From b009067de7916c40ebf0dbf5f7af296a51233fa0 Mon Sep 17 00:00:00 2001 From: Andrea Valassi Date: Sun, 15 Sep 2024 17:05:03 +0200 Subject: [PATCH] [v360] rerun 102 tput tests on itscrd90 (including Olivier's master_for360 #992, which includes his/my goodhel #955 and #986) - all ok STARTED AT Sun Sep 15 09:27:42 AM CEST 2024 ./tput/teeThroughputX.sh -mix -hrd -makej -eemumu -ggtt -ggttg -ggttgg -gqttq -ggttggg -makeclean ENDED(1) AT Sun Sep 15 11:28:15 AM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -flt -hrd -makej -eemumu -ggtt -ggttgg -inlonly -makeclean ENDED(2) AT Sun Sep 15 11:41:01 AM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -makej -eemumu -ggtt -ggttg -gqttq -ggttgg -ggttggg -flt -bridge -makeclean ENDED(3) AT Sun Sep 15 11:51:46 AM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -eemumu -ggtt -ggttgg -flt -rmbhst ENDED(4) AT Sun Sep 15 11:54:36 AM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -eemumu -ggtt -ggttgg -flt -curhst ENDED(5) AT Sun Sep 15 11:57:23 AM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -eemumu -ggtt -ggttgg -flt -common ENDED(6) AT Sun Sep 15 12:00:17 PM CEST 2024 [Status=0] ./tput/teeThroughputX.sh -mix -hrd -makej -susyggtt -susyggt1t1 -smeftggtttt -heftggbb -makeclean ENDED(7) AT Sun Sep 15 12:22:27 PM CEST 2024 [Status=0] --- .../log_eemumu_mad_d_inl0_hrd0.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl0_hrd0_bridge.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl0_hrd0_common.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl0_hrd0_curhst.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl0_hrd0_rmbhst.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl0_hrd1.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl1_hrd0.txt | 164 ++++++++-------- .../log_eemumu_mad_d_inl1_hrd1.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd0.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd0_bridge.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd0_common.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd0_curhst.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd0_rmbhst.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl0_hrd1.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl1_hrd0.txt | 164 ++++++++-------- .../log_eemumu_mad_f_inl1_hrd1.txt | 164 ++++++++-------- .../log_eemumu_mad_m_inl0_hrd0.txt | 164 ++++++++-------- .../log_eemumu_mad_m_inl0_hrd1.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd0.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd0_bridge.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd0_common.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd0_curhst.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd0_rmbhst.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl0_hrd1.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl1_hrd0.txt | 164 ++++++++-------- .../log_ggtt_mad_d_inl1_hrd1.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd0.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd0_bridge.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd0_common.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd0_curhst.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd0_rmbhst.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl0_hrd1.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl1_hrd0.txt | 164 ++++++++-------- .../log_ggtt_mad_f_inl1_hrd1.txt | 164 ++++++++-------- .../log_ggtt_mad_m_inl0_hrd0.txt | 164 ++++++++-------- .../log_ggtt_mad_m_inl0_hrd1.txt | 164 ++++++++-------- .../log_ggttg_mad_d_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttg_mad_d_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_ggttg_mad_d_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttg_mad_f_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttg_mad_f_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_ggttg_mad_f_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttg_mad_m_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttg_mad_m_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd0_common.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd0_curhst.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd0_rmbhst.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl1_hrd0.txt | 180 +++++++++--------- .../log_ggttgg_mad_d_inl1_hrd1.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd0_common.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd0_curhst.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd0_rmbhst.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl1_hrd0.txt | 180 +++++++++--------- .../log_ggttgg_mad_f_inl1_hrd1.txt | 180 +++++++++--------- .../log_ggttgg_mad_m_inl0_hrd0.txt | 180 +++++++++--------- .../log_ggttgg_mad_m_inl0_hrd1.txt | 180 +++++++++--------- .../log_ggttggg_mad_d_inl0_hrd0.txt | 156 +++++++-------- .../log_ggttggg_mad_d_inl0_hrd0_bridge.txt | 156 +++++++-------- .../log_ggttggg_mad_d_inl0_hrd1.txt | 156 +++++++-------- .../log_ggttggg_mad_f_inl0_hrd0.txt | 156 +++++++-------- .../log_ggttggg_mad_f_inl0_hrd0_bridge.txt | 156 +++++++-------- .../log_ggttggg_mad_f_inl0_hrd1.txt | 156 +++++++-------- .../log_ggttggg_mad_m_inl0_hrd0.txt | 156 +++++++-------- .../log_ggttggg_mad_m_inl0_hrd1.txt | 156 +++++++-------- .../log_gqttq_mad_d_inl0_hrd0.txt | 180 +++++++++--------- .../log_gqttq_mad_d_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_gqttq_mad_d_inl0_hrd1.txt | 180 +++++++++--------- .../log_gqttq_mad_f_inl0_hrd0.txt | 180 +++++++++--------- .../log_gqttq_mad_f_inl0_hrd0_bridge.txt | 180 +++++++++--------- .../log_gqttq_mad_f_inl0_hrd1.txt | 180 +++++++++--------- .../log_gqttq_mad_m_inl0_hrd0.txt | 180 +++++++++--------- .../log_gqttq_mad_m_inl0_hrd1.txt | 180 +++++++++--------- .../log_heftggbb_mad_d_inl0_hrd0.txt | 164 ++++++++-------- .../log_heftggbb_mad_d_inl0_hrd1.txt | 164 ++++++++-------- .../log_heftggbb_mad_f_inl0_hrd0.txt | 164 ++++++++-------- .../log_heftggbb_mad_f_inl0_hrd1.txt | 164 ++++++++-------- .../log_heftggbb_mad_m_inl0_hrd0.txt | 164 ++++++++-------- .../log_heftggbb_mad_m_inl0_hrd1.txt | 164 ++++++++-------- .../log_smeftggtttt_mad_d_inl0_hrd0.txt | 180 +++++++++--------- .../log_smeftggtttt_mad_d_inl0_hrd1.txt | 180 +++++++++--------- .../log_smeftggtttt_mad_f_inl0_hrd0.txt | 180 +++++++++--------- .../log_smeftggtttt_mad_f_inl0_hrd1.txt | 180 +++++++++--------- .../log_smeftggtttt_mad_m_inl0_hrd0.txt | 180 +++++++++--------- .../log_smeftggtttt_mad_m_inl0_hrd1.txt | 180 +++++++++--------- .../log_susyggt1t1_mad_d_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggt1t1_mad_d_inl0_hrd1.txt | 164 ++++++++-------- .../log_susyggt1t1_mad_f_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggt1t1_mad_f_inl0_hrd1.txt | 164 ++++++++-------- .../log_susyggt1t1_mad_m_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggt1t1_mad_m_inl0_hrd1.txt | 164 ++++++++-------- .../log_susyggtt_mad_d_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggtt_mad_d_inl0_hrd1.txt | 164 ++++++++-------- .../log_susyggtt_mad_f_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggtt_mad_f_inl0_hrd1.txt | 164 ++++++++-------- .../log_susyggtt_mad_m_inl0_hrd0.txt | 164 ++++++++-------- .../log_susyggtt_mad_m_inl0_hrd1.txt | 164 ++++++++-------- 102 files changed, 8652 insertions(+), 8652 deletions(-) diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt index 6dabcaead..1292ed24b 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:11:08 +DATE: 2024-09-15_11:08:03 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.316341e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.700853e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.825632e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.330379e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.527996e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.788543e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.678258 sec +TOTAL : 0.812638 sec INFO: No Floating Point Exceptions have been reported - 2,598,429,057 cycles # 2.870 GHz - 4,016,594,161 instructions # 1.55 insn per cycle - 0.970694128 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,711,766,628 cycles # 2.867 GHz + 4,239,903,132 instructions # 1.56 insn per cycle + 1.138564764 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.045966e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.218041e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.218041e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.032481e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.205909e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.205909e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.419615 sec +TOTAL : 6.541164 sec INFO: No Floating Point Exceptions have been reported - 19,020,182,633 cycles # 2.961 GHz - 46,088,995,833 instructions # 2.42 insn per cycle - 6.424712247 seconds time elapsed + 19,214,248,144 cycles # 2.933 GHz + 46,179,436,349 instructions # 2.40 insn per cycle + 6.552095575 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.554135e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.028420e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.028420e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.566602e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.052859e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.052859e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.470437 sec +TOTAL : 4.470271 sec INFO: No Floating Point Exceptions have been reported - 12,988,824,758 cycles # 2.911 GHz - 31,629,492,055 instructions # 2.44 insn per cycle - 4.475693569 seconds time elapsed + 13,145,357,361 cycles # 2.934 GHz + 31,720,883,797 instructions # 2.41 insn per cycle + 4.481479023 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1663) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.991760e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.780070e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.780070e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.961947e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.743984e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.743984e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.561283 sec +TOTAL : 3.647893 sec INFO: No Floating Point Exceptions have been reported - 10,090,609,279 cycles # 2.830 GHz - 19,603,699,574 instructions # 1.94 insn per cycle - 3.566410563 seconds time elapsed + 10,212,054,728 cycles # 2.792 GHz + 19,686,910,587 instructions # 1.93 insn per cycle + 3.658422867 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1912) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.057332e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.885467e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.885467e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.012892e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.837375e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.837375e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.457613 sec +TOTAL : 3.568887 sec INFO: No Floating Point Exceptions have been reported - 9,859,470,478 cycles # 2.848 GHz - 19,269,255,487 instructions # 1.95 insn per cycle - 3.462839764 seconds time elapsed + 10,042,390,879 cycles # 2.806 GHz + 19,342,891,969 instructions # 1.93 insn per cycle + 3.579550757 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1651) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.774988e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.357712e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.357712e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.687611e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.233598e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.233598e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.947870 sec +TOTAL : 4.179012 sec INFO: No Floating Point Exceptions have been reported - 8,591,487,226 cycles # 2.174 GHz - 15,733,547,778 instructions # 1.83 insn per cycle - 3.953082251 seconds time elapsed + 8,766,087,418 cycles # 2.093 GHz + 15,826,503,490 instructions # 1.81 insn per cycle + 4.190350116 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 848) (512y: 156) (512z: 1257) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_bridge.txt index c06c4fd58..656f6e2f9 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:41:41 +DATE: 2024-09-15_11:45:05 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.718927e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.650908e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.650908e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.206256e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.682542e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.682542e+07 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 2.222857 sec +TOTAL : 2.457281 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 7,357,681,022 cycles # 2.969 GHz - 13,116,457,275 instructions # 1.78 insn per cycle - 2.534653477 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge + 7,617,652,543 cycles # 2.830 GHz + 12,995,599,451 instructions # 1.71 insn per cycle + 2.778749807 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublocks*gputhreads=524288) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -79,35 +79,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.024615e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.188948e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.188948e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.578808e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.114252e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.114252e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.745071 sec +TOTAL : 7.297311 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 20,290,788,803 cycles # 3.006 GHz - 46,319,861,743 instructions # 2.28 insn per cycle - 6.751750408 seconds time elapsed + 20,775,260,342 cycles # 2.853 GHz + 46,581,102,942 instructions # 2.24 insn per cycle + 7.320240357 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -115,33 +115,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.540760e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.976659e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.976659e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.428539e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.841895e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.841895e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.692607 sec +TOTAL : 5.145544 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 14,149,693,879 cycles # 3.012 GHz - 32,468,658,455 instructions # 2.29 insn per cycle - 4.699232929 seconds time elapsed + 14,656,531,148 cycles # 2.850 GHz + 32,719,868,481 instructions # 2.23 insn per cycle + 5.168221991 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1663) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -149,33 +149,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.899701e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.593761e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.593761e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.782197e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.438081e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.438081e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.930700 sec +TOTAL : 4.265326 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 11,314,229,464 cycles # 2.874 GHz - 20,966,302,309 instructions # 1.85 insn per cycle - 3.937371007 seconds time elapsed + 11,667,988,214 cycles # 2.728 GHz + 21,208,810,330 instructions # 1.82 insn per cycle + 4.287433901 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1912) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -183,33 +183,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.940443e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.649272e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.649272e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.824257e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.501728e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.501728e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.855778 sec +TOTAL : 4.177936 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 11,163,065,611 cycles # 2.891 GHz - 20,629,365,545 instructions # 1.85 insn per cycle - 3.862281727 seconds time elapsed + 11,439,960,592 cycles # 2.728 GHz + 20,869,154,642 instructions # 1.82 insn per cycle + 4.198165961 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1651) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -217,33 +217,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.664453e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.162165e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.162165e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.555883e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.022583e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.022583e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.405270 sec +TOTAL : 4.778023 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 9,892,759,175 cycles # 2.243 GHz - 16,881,792,429 instructions # 1.71 insn per cycle - 4.412033088 seconds time elapsed + 10,270,194,102 cycles # 2.143 GHz + 17,125,695,085 instructions # 1.67 insn per cycle + 4.797944534 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 848) (512y: 156) (512z: 1257) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -251,8 +251,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_common.txt index 7182e1a44..c883b5b3b 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:53:41 +DATE: 2024-09-15_11:57:26 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.461368e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.445287e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.624818e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.026987e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.683583e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.857936e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 1.332517 sec +TOTAL : 1.462390 sec INFO: No Floating Point Exceptions have been reported - 4,633,809,881 cycles # 2.948 GHz - 7,263,887,198 instructions # 1.57 insn per cycle - 1.628488212 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common + 4,897,119,539 cycles # 2.892 GHz + 7,502,819,293 instructions # 1.53 insn per cycle + 1.751403177 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.048373e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.222413e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.222413e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.029304e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.201451e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.201451e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 6.768902 sec +TOTAL : 7.039422 sec INFO: No Floating Point Exceptions have been reported - 20,114,199,279 cycles # 2.970 GHz - 46,191,365,075 instructions # 2.30 insn per cycle - 6.774087692 seconds time elapsed + 20,621,489,655 cycles # 2.926 GHz + 46,653,049,885 instructions # 2.26 insn per cycle + 7.049549267 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.604747e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.094842e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.094842e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.563131e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.046448e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.046448e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 4.696978 sec +TOTAL : 4.950021 sec INFO: No Floating Point Exceptions have been reported - 14,035,189,999 cycles # 2.985 GHz - 31,625,158,467 instructions # 2.25 insn per cycle - 4.702368322 seconds time elapsed + 14,503,935,115 cycles # 2.925 GHz + 32,091,166,775 instructions # 2.21 insn per cycle + 4.960008276 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1663) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.023804e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.826844e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.826844e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.961733e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.745410e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.745410e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 3.873757 sec +TOTAL : 4.125348 sec INFO: No Floating Point Exceptions have been reported - 11,134,547,212 cycles # 2.871 GHz - 19,508,154,855 instructions # 1.75 insn per cycle - 3.879105882 seconds time elapsed + 11,625,768,108 cycles # 2.812 GHz + 19,969,403,537 instructions # 1.72 insn per cycle + 4.135325887 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1912) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.075999e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.926845e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.926845e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.013648e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.832922e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.832922e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 3.800700 sec +TOTAL : 4.042328 sec INFO: No Floating Point Exceptions have been reported - 10,969,458,533 cycles # 2.883 GHz - 18,956,382,786 instructions # 1.73 insn per cycle - 3.806025703 seconds time elapsed + 11,410,026,502 cycles # 2.817 GHz + 19,423,165,232 instructions # 1.70 insn per cycle + 4.052144921 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1651) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.779178e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.363282e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.363282e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.712486e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.267405e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.267405e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371879e-02 +- 3.270020e-06 ) GeV^0 -TOTAL : 4.314005 sec +TOTAL : 4.597004 sec INFO: No Floating Point Exceptions have been reported - 9,739,763,283 cycles # 2.256 GHz - 15,434,105,054 instructions # 1.58 insn per cycle - 4.319565293 seconds time elapsed + 10,166,885,638 cycles # 2.209 GHz + 15,890,691,650 instructions # 1.56 insn per cycle + 4.606740948 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 848) (512y: 156) (512z: 1257) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_curhst.txt index 33ead1e19..be71099ca 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:50:58 +DATE: 2024-09-15_11:54:39 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.500094e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.517548e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.743547e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.198136e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.691819e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.863296e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.980790 sec +TOTAL : 0.975349 sec INFO: No Floating Point Exceptions have been reported - 3,560,791,476 cycles # 2.941 GHz - 7,160,309,799 instructions # 2.01 insn per cycle - 1.268112972 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst + 3,491,422,658 cycles # 2.884 GHz + 6,978,748,855 instructions # 2.00 insn per cycle + 1.269405520 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.057662e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.232825e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.232825e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.025076e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.196021e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.196021e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.351364 sec +TOTAL : 6.587511 sec INFO: No Floating Point Exceptions have been reported - 19,028,703,027 cycles # 2.994 GHz - 46,088,094,034 instructions # 2.42 insn per cycle - 6.356654129 seconds time elapsed + 19,326,799,797 cycles # 2.930 GHz + 46,201,035,622 instructions # 2.39 insn per cycle + 6.597179522 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.610727e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.099544e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.099544e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.561064e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.042427e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.042427e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.309172 sec +TOTAL : 4.487009 sec INFO: No Floating Point Exceptions have been reported - 12,915,279,178 cycles # 2.994 GHz - 31,622,192,060 instructions # 2.45 insn per cycle - 4.314454195 seconds time elapsed + 13,122,812,956 cycles # 2.919 GHz + 31,726,329,549 instructions # 2.42 insn per cycle + 4.497261752 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1663) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.964702e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.728204e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.728204e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.964017e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.742650e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.742650e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.611197 sec +TOTAL : 3.652673 sec INFO: No Floating Point Exceptions have been reported - 10,072,475,407 cycles # 2.786 GHz - 19,603,807,541 instructions # 1.95 insn per cycle - 3.616483385 seconds time elapsed + 10,238,914,237 cycles # 2.798 GHz + 19,709,087,829 instructions # 1.92 insn per cycle + 3.662709498 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1912) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.073817e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.916083e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.916083e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.987318e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.812393e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.812393e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.432142 sec +TOTAL : 3.613935 sec INFO: No Floating Point Exceptions have been reported - 9,841,961,259 cycles # 2.864 GHz - 19,266,632,762 instructions # 1.96 insn per cycle - 3.437636381 seconds time elapsed + 10,087,966,707 cycles # 2.786 GHz + 19,370,511,659 instructions # 1.92 insn per cycle + 3.624175302 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1651) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.789510e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.380802e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.380802e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.729073e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.292942e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.292942e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.918568 sec +TOTAL : 4.086984 sec INFO: No Floating Point Exceptions have been reported - 8,610,059,548 cycles # 2.195 GHz - 15,735,305,253 instructions # 1.83 insn per cycle - 3.924031077 seconds time elapsed + 8,757,365,492 cycles # 2.138 GHz + 15,836,859,575 instructions # 1.81 insn per cycle + 4.097082998 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 848) (512y: 156) (512z: 1257) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_rmbhst.txt index bc9d647fb..1574c6c3c 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,60 +11,60 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:48:12 +DATE: 2024-09-15_11:51:49 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 12 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.122021e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.451137e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.638753e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.996142e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.634832e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.796610e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 1.870611 sec +TOTAL : 1.900321 sec INFO: No Floating Point Exceptions have been reported - 6,204,814,895 cycles # 2.954 GHz - 11,480,482,305 instructions # 1.85 insn per cycle - 2.157739025 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst + 6,197,801,426 cycles # 2.910 GHz + 11,411,789,503 instructions # 1.84 insn per cycle + 2.187318710 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -72,33 +72,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.059054e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.233189e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.233189e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.025883e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.199963e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.199963e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.345554 sec +TOTAL : 6.587430 sec INFO: No Floating Point Exceptions have been reported - 19,029,442,022 cycles # 2.997 GHz - 46,088,029,717 instructions # 2.42 insn per cycle - 6.350870900 seconds time elapsed + 19,281,256,149 cycles # 2.928 GHz + 46,192,094,635 instructions # 2.40 insn per cycle + 6.597986195 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -106,31 +106,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.610948e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.102172e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.102172e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.548679e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.019540e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.019540e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.312066 sec +TOTAL : 4.521143 sec INFO: No Floating Point Exceptions have been reported - 12,916,579,175 cycles # 2.992 GHz - 31,622,030,303 instructions # 2.45 insn per cycle - 4.317489305 seconds time elapsed + 13,278,378,525 cycles # 2.931 GHz + 31,736,760,460 instructions # 2.39 insn per cycle + 4.531295049 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1663) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -138,31 +138,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.024660e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.820920e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.820920e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.952371e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.722642e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.722642e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.509062 sec +TOTAL : 3.672885 sec INFO: No Floating Point Exceptions have been reported - 10,061,648,485 cycles # 2.864 GHz - 19,603,502,379 instructions # 1.95 insn per cycle - 3.514567609 seconds time elapsed + 10,228,932,843 cycles # 2.778 GHz + 19,706,958,837 instructions # 1.93 insn per cycle + 3.682647007 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1912) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -170,31 +170,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.076351e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.915963e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.915963e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.003393e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.813864e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.813864e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.426777 sec +TOTAL : 3.587790 sec INFO: No Floating Point Exceptions have been reported - 9,851,026,234 cycles # 2.871 GHz - 19,268,085,761 instructions # 1.96 insn per cycle - 3.432072497 seconds time elapsed + 10,033,694,863 cycles # 2.790 GHz + 19,370,562,804 instructions # 1.93 insn per cycle + 3.597832664 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1651) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -202,31 +202,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.788696e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.373983e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.373983e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.709775e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.272417e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.272417e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.919489 sec +TOTAL : 4.131241 sec INFO: No Floating Point Exceptions have been reported - 8,601,360,723 cycles # 2.192 GHz - 15,734,373,866 instructions # 1.83 insn per cycle - 3.924666234 seconds time elapsed + 8,787,275,470 cycles # 2.123 GHz + 15,836,849,319 instructions # 1.80 insn per cycle + 4.141346630 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 848) (512y: 156) (512z: 1257) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -234,8 +234,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd1.txt index d94fcbe33..3b02782d4 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:11:39 +DATE: 2024-09-15_11:08:35 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.432610e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.772959e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.942951e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.564401e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.700588e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.875805e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.656283 sec +TOTAL : 0.684524 sec INFO: No Floating Point Exceptions have been reported - 2,600,163,483 cycles # 2.927 GHz - 4,052,933,946 instructions # 1.56 insn per cycle - 0.947198008 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,669,304,279 cycles # 2.860 GHz + 4,081,785,887 instructions # 1.53 insn per cycle + 0.991787338 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 154 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.040048e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.211774e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.211774e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.030249e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.204005e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.204005e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.455813 sec +TOTAL : 6.555775 sec INFO: No Floating Point Exceptions have been reported - 19,047,161,782 cycles # 2.949 GHz - 46,053,166,008 instructions # 2.42 insn per cycle - 6.460830735 seconds time elapsed + 19,264,579,235 cycles # 2.934 GHz + 46,142,725,089 instructions # 2.40 insn per cycle + 6.567398103 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 452) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.605833e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.090868e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.090868e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.561230e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.041001e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.041001e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.322171 sec +TOTAL : 4.486484 sec INFO: No Floating Point Exceptions have been reported - 12,945,614,006 cycles # 2.992 GHz - 31,599,414,213 instructions # 2.44 insn per cycle - 4.327245745 seconds time elapsed + 13,180,735,522 cycles # 2.931 GHz + 31,698,753,932 instructions # 2.40 insn per cycle + 4.497601224 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1649) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.012855e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.814007e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.814007e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.959717e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.742175e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.742175e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.527895 sec +TOTAL : 3.661759 sec INFO: No Floating Point Exceptions have been reported - 10,083,243,360 cycles # 2.855 GHz - 19,584,052,787 instructions # 1.94 insn per cycle - 3.532820504 seconds time elapsed + 10,296,251,645 cycles # 2.804 GHz + 19,686,624,933 instructions # 1.91 insn per cycle + 3.673145773 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1895) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165090E-002 Relative difference = 1.0277089176796747e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.040603e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.875933e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.875933e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.002735e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.826033e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.826033e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.488013 sec +TOTAL : 3.593177 sec INFO: No Floating Point Exceptions have been reported - 9,881,550,683 cycles # 2.830 GHz - 19,282,348,908 instructions # 1.95 insn per cycle - 3.493036517 seconds time elapsed + 10,082,197,083 cycles # 2.798 GHz + 19,384,360,663 instructions # 1.92 insn per cycle + 3.604587412 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1636) (512y: 178) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165090E-002 Relative difference = 1.0277089176796747e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.829130e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.446924e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.446924e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.753760e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.344313e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.344313e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.841542 sec +TOTAL : 4.042847 sec INFO: No Floating Point Exceptions have been reported - 8,444,886,940 cycles # 2.196 GHz - 15,604,417,284 instructions # 1.85 insn per cycle - 3.846602501 seconds time elapsed + 8,657,274,459 cycles # 2.136 GHz + 15,708,080,882 instructions # 1.81 insn per cycle + 4.054289402 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 834) (512y: 156) (512z: 1237) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd0.txt index 94cb4ff06..9adc226af 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:32:12 +DATE: 2024-09-15_11:33:55 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.929041e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.617382e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.790354e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.203471e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.505439e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.793875e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.673044 sec +TOTAL : 0.692895 sec INFO: No Floating Point Exceptions have been reported - 2,647,663,893 cycles # 2.921 GHz - 4,117,337,322 instructions # 1.56 insn per cycle - 0.970576149 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 + 2,667,104,303 cycles # 2.870 GHz + 4,197,568,068 instructions # 1.57 insn per cycle + 0.991023921 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.635868e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.098681e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.098681e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.609773e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.065122e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.065122e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.251149 sec +TOTAL : 4.323744 sec INFO: No Floating Point Exceptions have been reported - 12,685,973,484 cycles # 2.981 GHz - 32,572,050,993 instructions # 2.57 insn per cycle - 4.256454263 seconds time elapsed + 12,680,899,676 cycles # 2.930 GHz + 32,573,373,461 instructions # 2.57 insn per cycle + 4.329822925 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 281) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.069872e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.953267e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.953267e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.020941e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.881765e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.881765e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.446136 sec +TOTAL : 3.528541 sec INFO: No Floating Point Exceptions have been reported - 10,327,366,247 cycles # 2.993 GHz - 24,660,690,745 instructions # 2.39 insn per cycle - 3.451551574 seconds time elapsed + 10,343,960,768 cycles # 2.928 GHz + 24,660,363,232 instructions # 2.38 insn per cycle + 3.534351751 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1251) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.268023e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.332197e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.332197e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.219408e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.252697e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.252697e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.179322 sec +TOTAL : 3.248651 sec INFO: No Floating Point Exceptions have been reported - 9,101,042,758 cycles # 2.859 GHz - 16,944,009,823 instructions # 1.86 insn per cycle - 3.184712944 seconds time elapsed + 9,122,079,188 cycles # 2.804 GHz + 16,949,443,243 instructions # 1.86 insn per cycle + 3.254977824 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1616) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.323659e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.427846e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.427846e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.281631e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.372235e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.372235e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.107460 sec +TOTAL : 3.167737 sec INFO: No Floating Point Exceptions have been reported - 8,903,453,254 cycles # 2.861 GHz - 16,358,754,262 instructions # 1.84 insn per cycle - 3.112772356 seconds time elapsed + 8,922,630,281 cycles # 2.812 GHz + 16,368,012,425 instructions # 1.83 insn per cycle + 3.174211351 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1352) (512y: 139) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.012554e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.786256e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.786256e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.953386e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.685128e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.685128e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.528360 sec +TOTAL : 3.635921 sec INFO: No Floating Point Exceptions have been reported - 7,891,857,406 cycles # 2.234 GHz - 14,578,880,134 instructions # 1.85 insn per cycle - 3.533675166 seconds time elapsed + 7,907,839,436 cycles # 2.172 GHz + 14,593,864,068 instructions # 1.85 insn per cycle + 3.642895717 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1003) (512y: 158) (512z: 955) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd1.txt index aeece3cb1..a111e191c 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:32:40 +DATE: 2024-09-15_11:34:21 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.944309e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.640485e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.841925e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.369824e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.600320e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.803756e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.670764 sec +TOTAL : 0.688866 sec INFO: No Floating Point Exceptions have been reported - 2,641,145,737 cycles # 2.922 GHz - 4,081,113,697 instructions # 1.55 insn per cycle - 0.966027510 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 + 2,687,883,365 cycles # 2.879 GHz + 4,137,672,828 instructions # 1.54 insn per cycle + 0.991982760 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 154 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039868165201E-002 Relative difference = 1.0277080522138477e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_d_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.130231e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.983916e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.983916e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.085552e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.924035e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.924035e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.355515 sec +TOTAL : 3.430840 sec INFO: No Floating Point Exceptions have been reported - 10,000,706,305 cycles # 2.977 GHz - 25,508,878,851 instructions # 2.55 insn per cycle - 3.360784759 seconds time elapsed + 10,018,256,596 cycles # 2.916 GHz + 25,507,694,274 instructions # 2.55 insn per cycle + 3.436494229 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 236) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.421455e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.716932e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.716932e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.371301e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.639987e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.639987e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.001722 sec +TOTAL : 3.073954 sec INFO: No Floating Point Exceptions have been reported - 9,011,683,226 cycles # 2.998 GHz - 21,468,272,813 instructions # 2.38 insn per cycle - 3.007077981 seconds time elapsed + 9,025,495,783 cycles # 2.931 GHz + 21,478,170,721 instructions # 2.38 insn per cycle + 3.080490687 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1100) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868164916E-002 Relative difference = 1.0277102699700292e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.418837e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.668858e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.668858e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.348565e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.529213e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.529213e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.000616 sec +TOTAL : 3.091062 sec INFO: No Floating Point Exceptions have been reported - 8,681,159,666 cycles # 2.889 GHz - 15,895,078,651 instructions # 1.83 insn per cycle - 3.006012376 seconds time elapsed + 8,721,037,733 cycles # 2.816 GHz + 15,901,191,500 instructions # 1.82 insn per cycle + 3.097416237 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1489) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.476533e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.780002e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.780002e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.428348e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.696607e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.696607e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 2.939228 sec +TOTAL : 3.003427 sec INFO: No Floating Point Exceptions have been reported - 8,461,049,520 cycles # 2.875 GHz - 15,605,360,429 instructions # 1.84 insn per cycle - 2.944460500 seconds time elapsed + 8,472,649,935 cycles # 2.816 GHz + 15,622,192,614 instructions # 1.84 insn per cycle + 3.009695803 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1264) (512y: 141) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.080846e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.942278e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.942278e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.053185e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.879921e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.879921e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.429466 sec +TOTAL : 3.481285 sec INFO: No Floating Point Exceptions have been reported - 7,594,294,635 cycles # 2.211 GHz - 14,291,461,453 instructions # 1.88 insn per cycle - 3.434950736 seconds time elapsed + 7,632,139,448 cycles # 2.189 GHz + 14,304,829,590 instructions # 1.87 insn per cycle + 3.488200715 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1032) (512y: 164) (512z: 877) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039868165088E-002 Relative difference = 1.0277089312025782e-08 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0.txt index f57c7b21b..bc5233a5b 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:12:09 +DATE: 2024-09-15_11:09:06 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.440125e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.939612e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.936542e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.192132e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.336696e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.300693e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371687e-02 +- 3.270220e-06 ) GeV^0 -TOTAL : 0.569720 sec +TOTAL : 0.585451 sec INFO: No Floating Point Exceptions have been reported - 2,292,199,788 cycles # 2.893 GHz - 3,624,722,505 instructions # 1.58 insn per cycle - 0.851143724 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,336,870,734 cycles # 2.880 GHz + 3,644,936,097 instructions # 1.56 insn per cycle + 0.870296260 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.092122e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.295282e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.295282e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.072651e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.269381e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.269381e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 6.123236 sec +TOTAL : 6.255061 sec INFO: No Floating Point Exceptions have been reported - 18,282,268,739 cycles # 2.985 GHz - 45,003,688,571 instructions # 2.46 insn per cycle - 6.127863395 seconds time elapsed + 18,355,246,050 cycles # 2.931 GHz + 45,043,077,667 instructions # 2.45 insn per cycle + 6.263286658 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 411) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.300657e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.500016e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.500016e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.241713e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.430745e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.430745e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.101147 sec +TOTAL : 3.200925 sec INFO: No Floating Point Exceptions have been reported - 9,272,391,340 cycles # 2.986 GHz - 22,287,274,481 instructions # 2.40 insn per cycle - 3.106124711 seconds time elapsed + 9,386,491,422 cycles # 2.926 GHz + 22,329,398,339 instructions # 2.38 insn per cycle + 3.208910381 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1956) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.435250e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.745190e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.745190e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.404117e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.697492e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.697492e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.946093 sec +TOTAL : 3.006682 sec INFO: No Floating Point Exceptions have been reported - 8,415,505,503 cycles # 2.853 GHz - 15,755,045,400 instructions # 1.87 insn per cycle - 2.951003636 seconds time elapsed + 8,484,958,572 cycles # 2.815 GHz + 15,797,352,563 instructions # 1.86 insn per cycle + 3.014624816 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2564) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.503188e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.850723e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.850723e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.426806e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.765840e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.765840e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.877500 sec +TOTAL : 2.982618 sec INFO: No Floating Point Exceptions have been reported - 8,240,649,806 cycles # 2.860 GHz - 15,608,293,943 instructions # 1.89 insn per cycle - 2.882240516 seconds time elapsed + 8,401,165,701 cycles # 2.811 GHz + 15,653,777,374 instructions # 1.86 insn per cycle + 2.990373231 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2467) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.533350e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.890104e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.890104e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.426463e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.722731e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.722731e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.848263 sec +TOTAL : 2.987827 sec INFO: No Floating Point Exceptions have been reported - 6,616,696,344 cycles # 2.320 GHz - 12,864,238,029 instructions # 1.94 insn per cycle - 2.853239358 seconds time elapsed + 6,753,744,387 cycles # 2.255 GHz + 12,906,211,238 instructions # 1.91 insn per cycle + 2.995926915 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1697) (512y: 17) (512z: 1440) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052585973637E-002 Relative difference = 2.0158743040564767e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_bridge.txt index 35a9e5f0a..95b868152 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:42:15 +DATE: 2024-09-15_11:45:42 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.205566e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.525744e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.525744e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.076713e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.378449e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.378449e+07 ) sec^-1 MeanMatrixElemValue = ( 1.371710e-02 +- 3.270389e-06 ) GeV^0 -TOTAL : 1.687596 sec +TOTAL : 1.944337 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 5,641,583,670 cycles # 2.942 GHz - 10,304,772,583 instructions # 1.83 insn per cycle - 1.974857486 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge + 6,200,765,179 cycles # 2.831 GHz + 10,073,714,089 instructions # 1.62 insn per cycle + 2.274311561 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublocks*gputhreads=524288) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -79,35 +79,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.078790e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.269966e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.269966e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.013177e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.196081e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.196081e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 6.303292 sec +TOTAL : 6.753252 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 18,887,037,403 cycles # 2.994 GHz - 45,157,662,858 instructions # 2.39 insn per cycle - 6.309618883 seconds time elapsed + 19,140,260,721 cycles # 2.851 GHz + 45,281,984,182 instructions # 2.37 insn per cycle + 6.770979415 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 411) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -115,33 +115,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.206720e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.289779e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.289779e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.075255e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.101362e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.101362e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.339455 sec +TOTAL : 3.587325 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 10,009,397,596 cycles # 2.993 GHz - 23,624,007,980 instructions # 2.36 insn per cycle - 3.345685257 seconds time elapsed + 10,243,661,246 cycles # 2.856 GHz + 23,736,113,257 instructions # 2.32 insn per cycle + 3.601313820 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1956) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -149,33 +149,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.372007e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.557809e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.557809e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.208611e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.299964e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.299964e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 3.134578 sec +TOTAL : 3.407535 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 9,093,525,796 cycles # 2.896 GHz - 16,876,695,371 instructions # 1.86 insn per cycle - 3.140803970 seconds time elapsed + 9,325,104,909 cycles # 2.739 GHz + 16,992,883,294 instructions # 1.82 insn per cycle + 3.420829574 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2564) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -183,33 +183,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.406670e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.628174e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.628174e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.223475e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.357947e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.357947e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 3.100606 sec +TOTAL : 3.391442 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 8,981,201,315 cycles # 2.892 GHz - 16,731,017,995 instructions # 1.86 insn per cycle - 3.106832833 seconds time elapsed + 9,279,675,392 cycles # 2.737 GHz + 16,862,711,706 instructions # 1.82 insn per cycle + 3.405369019 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2467) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -217,33 +217,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.401752e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.585254e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.585254e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.268012e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.359028e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.359028e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 3.116972 sec +TOTAL : 3.328677 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 7,400,362,239 cycles # 2.371 GHz - 14,073,208,836 instructions # 1.90 insn per cycle - 3.123177526 seconds time elapsed + 7,543,875,114 cycles # 2.260 GHz + 14,180,005,728 instructions # 1.88 insn per cycle + 3.340981281 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1697) (512y: 17) (512z: 1440) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -251,8 +251,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052585973637E-002 Relative difference = 2.0158743040564767e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_common.txt index a657a65df..15fa7d311 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:54:14 +DATE: 2024-09-15_11:58:00 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.247248e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.173509e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.063213e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.336762e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.510278e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.479828e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371863e-02 +- 3.269951e-06 ) GeV^0 -TOTAL : 1.182559 sec +TOTAL : 1.311031 sec INFO: No Floating Point Exceptions have been reported - 4,144,228,991 cycles # 2.949 GHz - 6,631,660,348 instructions # 1.60 insn per cycle - 1.462664969 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common + 4,430,467,531 cycles # 2.889 GHz + 6,960,795,222 instructions # 1.57 insn per cycle + 1.590735457 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.086369e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.285646e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.285646e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.075223e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.270769e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.270769e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371887e-02 +- 3.270267e-06 ) GeV^0 -TOTAL : 6.497519 sec +TOTAL : 6.687798 sec INFO: No Floating Point Exceptions have been reported - 19,270,516,007 cycles # 2.964 GHz - 45,188,255,066 instructions # 2.34 insn per cycle - 6.502716523 seconds time elapsed + 19,629,378,634 cycles # 2.933 GHz + 45,588,143,016 instructions # 2.32 insn per cycle + 6.694819566 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 411) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.305512e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.522941e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.522941e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.248280e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.433718e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.433718e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371887e-02 +- 3.270266e-06 ) GeV^0 -TOTAL : 3.424680 sec +TOTAL : 3.634348 sec INFO: No Floating Point Exceptions have been reported - 10,285,963,197 cycles # 3.000 GHz - 22,368,079,047 instructions # 2.17 insn per cycle - 3.429925704 seconds time elapsed + 10,674,006,930 cycles # 2.932 GHz + 22,771,305,471 instructions # 2.13 insn per cycle + 3.641620548 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1956) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.479341e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.792000e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.792000e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.377112e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.647798e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.647798e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371885e-02 +- 3.270112e-06 ) GeV^0 -TOTAL : 3.229115 sec +TOTAL : 3.480978 sec INFO: No Floating Point Exceptions have been reported - 9,380,692,116 cycles # 2.902 GHz - 15,667,536,193 instructions # 1.67 insn per cycle - 3.234097773 seconds time elapsed + 9,770,888,729 cycles # 2.802 GHz + 16,055,948,307 instructions # 1.64 insn per cycle + 3.487814115 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2564) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.511800e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.864478e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.864478e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.421430e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.770475e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.770475e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371885e-02 +- 3.270112e-06 ) GeV^0 -TOTAL : 3.204591 sec +TOTAL : 3.434581 sec INFO: No Floating Point Exceptions have been reported - 9,285,052,446 cycles # 2.894 GHz - 15,324,225,187 instructions # 1.65 insn per cycle - 3.209705429 seconds time elapsed + 9,740,474,003 cycles # 2.831 GHz + 15,722,386,015 instructions # 1.61 insn per cycle + 3.441655213 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2467) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.530155e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.885798e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.885798e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.441505e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.731463e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.731463e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371885e-02 +- 3.270112e-06 ) GeV^0 -TOTAL : 3.192143 sec +TOTAL : 3.419856 sec INFO: No Floating Point Exceptions have been reported - 7,665,193,061 cycles # 2.398 GHz - 12,573,697,492 instructions # 1.64 insn per cycle - 3.197431615 seconds time elapsed + 8,031,724,309 cycles # 2.344 GHz + 12,960,768,751 instructions # 1.61 insn per cycle + 3.427508239 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1697) (512y: 17) (512z: 1440) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052585973637E-002 Relative difference = 2.0158743040564767e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_curhst.txt index 8c6a0f3af..cd1edf8b0 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:51:28 +DATE: 2024-09-15_11:55:10 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.262526e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.390328e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.387630e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.341129e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.656597e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.613096e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371687e-02 +- 3.270220e-06 ) GeV^0 -TOTAL : 0.856218 sec +TOTAL : 0.860917 sec INFO: No Floating Point Exceptions have been reported - 3,161,544,131 cycles # 2.937 GHz - 6,517,835,009 instructions # 2.06 insn per cycle - 1.134957109 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst + 3,166,806,232 cycles # 2.886 GHz + 6,390,531,049 instructions # 2.02 insn per cycle + 1.154020491 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.096959e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.295586e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.295586e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.067801e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.267766e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.267766e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 6.095656 sec +TOTAL : 6.288953 sec INFO: No Floating Point Exceptions have been reported - 18,241,874,835 cycles # 2.990 GHz - 45,006,676,387 instructions # 2.47 insn per cycle - 6.100863007 seconds time elapsed + 18,410,332,076 cycles # 2.925 GHz + 45,054,816,993 instructions # 2.45 insn per cycle + 6.296062030 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 411) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.302660e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.506502e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.506502e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.250758e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.437877e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.437877e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.102726 sec +TOTAL : 3.189367 sec INFO: No Floating Point Exceptions have been reported - 9,285,265,734 cycles # 2.989 GHz - 22,287,225,294 instructions # 2.40 insn per cycle - 3.107827990 seconds time elapsed + 9,348,605,615 cycles # 2.926 GHz + 22,330,060,575 instructions # 2.39 insn per cycle + 3.196473636 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1956) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.467927e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.777181e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.777181e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.398564e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.676038e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.676038e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.912326 sec +TOTAL : 3.014863 sec INFO: No Floating Point Exceptions have been reported - 8,373,944,597 cycles # 2.872 GHz - 15,754,624,876 instructions # 1.88 insn per cycle - 2.917669267 seconds time elapsed + 8,484,963,512 cycles # 2.808 GHz + 15,797,579,651 instructions # 1.86 insn per cycle + 3.022063297 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2564) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.499171e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.843892e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.843892e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.428672e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.765186e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.765186e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.880358 sec +TOTAL : 2.974553 sec INFO: No Floating Point Exceptions have been reported - 8,253,904,909 cycles # 2.861 GHz - 15,614,471,146 instructions # 1.89 insn per cycle - 2.885437824 seconds time elapsed + 8,386,796,916 cycles # 2.814 GHz + 15,657,891,969 instructions # 1.87 insn per cycle + 2.981555653 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2467) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.523885e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.854007e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.854007e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.445697e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.728486e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.728486e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.856554 sec +TOTAL : 2.962981 sec INFO: No Floating Point Exceptions have been reported - 6,625,726,004 cycles # 2.316 GHz - 12,865,251,919 instructions # 1.94 insn per cycle - 2.861676497 seconds time elapsed + 6,681,340,868 cycles # 2.251 GHz + 12,907,012,003 instructions # 1.93 insn per cycle + 2.970184514 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1697) (512y: 17) (512z: 1440) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052585973637E-002 Relative difference = 2.0158743040564767e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_rmbhst.txt index fb5ea9b7e..6589d6b6f 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,60 +11,60 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:48:43 +DATE: 2024-09-15_11:52:21 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 12 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.018326e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.328781e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.289875e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.003631e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.641927e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.671119e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371710e-02 +- 3.270389e-06 ) GeV^0 -TOTAL : 1.485303 sec +TOTAL : 1.488823 sec INFO: No Floating Point Exceptions have been reported - 5,030,861,863 cycles # 2.949 GHz - 9,228,129,648 instructions # 1.83 insn per cycle - 1.764637764 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst + 4,967,613,517 cycles # 2.899 GHz + 9,171,831,308 instructions # 1.85 insn per cycle + 1.769936667 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -72,33 +72,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.101305e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.300250e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.300250e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.073262e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.267974e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.267974e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 6.075575 sec +TOTAL : 6.250612 sec INFO: No Floating Point Exceptions have been reported - 18,237,738,264 cycles # 3.000 GHz - 45,006,180,430 instructions # 2.47 insn per cycle - 6.080723981 seconds time elapsed + 18,322,110,309 cycles # 2.929 GHz + 45,051,388,062 instructions # 2.46 insn per cycle + 6.257775360 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 411) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -106,31 +106,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.297930e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.508269e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.508269e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.247339e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.424409e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.424409e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.101909 sec +TOTAL : 3.190677 sec INFO: No Floating Point Exceptions have been reported - 9,293,555,965 cycles # 2.992 GHz - 22,286,993,678 instructions # 2.40 insn per cycle - 3.107037940 seconds time elapsed + 9,359,387,266 cycles # 2.928 GHz + 22,331,498,291 instructions # 2.39 insn per cycle + 3.197654484 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1956) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -138,31 +138,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.452818e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.733465e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.733465e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.363785e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.679448e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.679448e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.926757 sec +TOTAL : 3.047896 sec INFO: No Floating Point Exceptions have been reported - 8,366,818,253 cycles # 2.855 GHz - 15,756,195,031 instructions # 1.88 insn per cycle - 2.931860697 seconds time elapsed + 8,583,132,130 cycles # 2.811 GHz + 15,806,350,534 instructions # 1.84 insn per cycle + 3.054826008 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2564) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -170,31 +170,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.524375e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.884976e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.884976e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.430638e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.771124e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.771124e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.852545 sec +TOTAL : 2.974287 sec INFO: No Floating Point Exceptions have been reported - 8,237,825,361 cycles # 2.884 GHz - 15,608,755,520 instructions # 1.89 insn per cycle - 2.857595702 seconds time elapsed + 8,401,059,167 cycles # 2.818 GHz + 15,651,581,046 instructions # 1.86 insn per cycle + 2.981875735 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2467) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -202,31 +202,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 12 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.526966e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.890608e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.890608e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.438697e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.736996e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.736996e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.855239 sec +TOTAL : 2.973534 sec INFO: No Floating Point Exceptions have been reported - 6,638,810,786 cycles # 2.322 GHz - 12,863,885,814 instructions # 1.94 insn per cycle - 2.860360436 seconds time elapsed + 6,722,109,548 cycles # 2.256 GHz + 12,906,606,049 instructions # 1.92 insn per cycle + 2.981153680 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1697) (512y: 17) (512z: 1440) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -234,8 +234,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052585973637E-002 Relative difference = 2.0158743040564767e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd1.txt index 00eaba46f..bed528f6e 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:12:35 +DATE: 2024-09-15_11:09:33 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.447555e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.168245e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.316057e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.185244e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.645179e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.802907e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371687e-02 +- 3.270220e-06 ) GeV^0 -TOTAL : 0.567766 sec +TOTAL : 0.581560 sec INFO: No Floating Point Exceptions have been reported - 2,287,776,846 cycles # 2.893 GHz - 3,650,539,912 instructions # 1.60 insn per cycle - 0.849995377 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,321,713,730 cycles # 2.869 GHz + 3,648,873,879 instructions # 1.57 insn per cycle + 0.865547071 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 79 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.093159e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.289183e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.289183e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.067642e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.262437e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.262437e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 6.118530 sec +TOTAL : 6.278398 sec INFO: No Floating Point Exceptions have been reported - 18,272,965,628 cycles # 2.985 GHz - 44,981,058,442 instructions # 2.46 insn per cycle - 6.123441325 seconds time elapsed + 18,394,901,899 cycles # 2.927 GHz + 45,013,341,285 instructions # 2.45 insn per cycle + 6.286516700 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 397) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039854866802E-002 Relative difference = 1.1313746984080878e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.227466e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.393043e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.393043e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.249815e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.432877e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.432877e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.201221 sec +TOTAL : 3.188261 sec INFO: No Floating Point Exceptions have been reported - 9,275,282,455 cycles # 2.894 GHz - 22,254,657,541 instructions # 2.40 insn per cycle - 3.206036710 seconds time elapsed + 9,382,779,388 cycles # 2.937 GHz + 22,291,184,899 instructions # 2.38 insn per cycle + 3.196123670 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1939) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.467502e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.773696e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.773696e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.394804e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.683014e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.683014e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.910424 sec +TOTAL : 3.016616 sec INFO: No Floating Point Exceptions have been reported - 8,366,603,031 cycles # 2.871 GHz - 15,747,210,395 instructions # 1.88 insn per cycle - 2.915453077 seconds time elapsed + 8,501,260,075 cycles # 2.812 GHz + 15,791,303,131 instructions # 1.86 insn per cycle + 3.024850695 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2539) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.509019e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.861570e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.861570e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.433401e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.784502e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.784502e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.868356 sec +TOTAL : 2.973425 sec INFO: No Floating Point Exceptions have been reported - 8,253,227,438 cycles # 2.873 GHz - 15,590,446,238 instructions # 1.89 insn per cycle - 2.873277360 seconds time elapsed + 8,414,276,106 cycles # 2.823 GHz + 15,633,261,481 instructions # 1.86 insn per cycle + 2.981340876 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2436) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053255361738E-002 Relative difference = 2.5376902468575066e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.537998e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.900122e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.900122e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.449856e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.750896e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.750896e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.844576 sec +TOTAL : 2.962493 sec INFO: No Floating Point Exceptions have been reported - 6,605,768,385 cycles # 2.322 GHz - 12,840,284,625 instructions # 1.94 insn per cycle - 2.849472031 seconds time elapsed + 6,702,761,235 cycles # 2.257 GHz + 12,885,740,598 instructions # 1.92 insn per cycle + 2.970728824 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1667) (512y: 18) (512z: 1428) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052564145764E-002 Relative difference = 1.9988585667912256e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd0.txt index f0525a51b..711fbf3a5 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:33:04 +DATE: 2024-09-15_11:34:45 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.346385e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.706042e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.743361e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.272057e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.453757e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.411368e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371687e-02 +- 3.270220e-06 ) GeV^0 -TOTAL : 0.570463 sec +TOTAL : 0.577320 sec INFO: No Floating Point Exceptions have been reported - 2,331,559,602 cycles # 2.930 GHz - 3,691,953,100 instructions # 1.58 insn per cycle - 0.853068830 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 + 2,322,367,280 cycles # 2.881 GHz + 3,616,476,077 instructions # 1.56 insn per cycle + 0.862621614 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 109 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.672409e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.178714e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.178714e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.635657e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.129532e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.129532e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 4.122248 sec +TOTAL : 4.218771 sec INFO: No Floating Point Exceptions have been reported - 12,193,246,018 cycles # 2.955 GHz - 32,297,778,851 instructions # 2.65 insn per cycle - 4.127366635 seconds time elapsed + 12,191,913,623 cycles # 2.887 GHz + 32,293,306,178 instructions # 2.65 insn per cycle + 4.224304323 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 290) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039840314887E-002 Relative difference = 1.244813035273009e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.726003e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.613506e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.613506e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.654215e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.464911e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.464911e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 2.677890 sec +TOTAL : 2.746425 sec INFO: No Floating Point Exceptions have been reported - 7,975,411,172 cycles # 2.973 GHz - 18,722,844,123 instructions # 2.35 insn per cycle - 2.683225038 seconds time elapsed + 8,013,864,577 cycles # 2.914 GHz + 18,725,751,725 instructions # 2.34 insn per cycle + 2.751635696 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1548) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039283704129E-002 Relative difference = 5.583829420356249e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.810407e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.657488e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.657488e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.734762e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.516819e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.516819e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.603296 sec +TOTAL : 2.676523 sec INFO: No Floating Point Exceptions have been reported - 7,478,624,708 cycles # 2.868 GHz - 14,257,879,880 instructions # 1.91 insn per cycle - 2.608417178 seconds time elapsed + 7,476,186,846 cycles # 2.791 GHz + 14,257,923,546 instructions # 1.91 insn per cycle + 2.682062632 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2237) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053244447801E-002 Relative difference = 2.5291823782248813e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.894749e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.863066e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.863066e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.834242e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.778618e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.778618e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.537757 sec +TOTAL : 2.592675 sec INFO: No Floating Point Exceptions have been reported - 7,332,061,078 cycles # 2.884 GHz - 13,960,145,042 instructions # 1.90 insn per cycle - 2.542891951 seconds time elapsed + 7,344,696,907 cycles # 2.828 GHz + 13,952,931,831 instructions # 1.90 insn per cycle + 2.598198803 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2087) (512y: 3) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053244447801E-002 Relative difference = 2.5291823782248813e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.593845e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.034171e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.034171e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.491060e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.875896e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.875896e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.793516 sec +TOTAL : 2.903149 sec INFO: No Floating Point Exceptions have been reported - 6,517,481,617 cycles # 2.329 GHz - 13,435,057,935 instructions # 2.06 insn per cycle - 2.798703190 seconds time elapsed + 6,571,286,194 cycles # 2.260 GHz + 13,433,545,963 instructions # 2.04 insn per cycle + 2.908820313 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2077) (512y: 1) (512z: 1199) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052562326775E-002 Relative difference = 1.997440588685788e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd1.txt index bd20a7074..6fc527ffa 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_f_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:33:27 +DATE: 2024-09-15_11:35:09 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.351814e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.868103e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.009929e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.289380e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.618768e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.817817e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371687e-02 +- 3.270220e-06 ) GeV^0 -TOTAL : 0.574031 sec +TOTAL : 0.580301 sec INFO: No Floating Point Exceptions have been reported - 2,336,591,618 cycles # 2.929 GHz - 3,652,107,547 instructions # 1.56 insn per cycle - 0.856248359 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 + 2,323,629,755 cycles # 2.848 GHz + 3,593,641,981 instructions # 1.55 insn per cycle + 0.873274895 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 79 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282802e-02 Avg ME (F77/GPU) = 1.2828112125134794E-002 Relative difference = 7.1815552823662555e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_f_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.220207e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.240567e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.240567e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.209448e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.220446e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.220446e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 3.196282 sec +TOTAL : 3.220192 sec INFO: No Floating Point Exceptions have been reported - 9,413,750,643 cycles # 2.941 GHz - 25,704,588,109 instructions # 2.73 insn per cycle - 3.201438558 seconds time elapsed + 9,366,774,041 cycles # 2.905 GHz + 25,702,432,609 instructions # 2.74 insn per cycle + 3.225730639 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 243) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039838495897E-002 Relative difference = 1.2589928273811243e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.045043e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.666844e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.666844e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.014104e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.557363e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.557363e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371707e-02 +- 3.270376e-06 ) GeV^0 -TOTAL : 2.433842 sec +TOTAL : 2.462960 sec INFO: No Floating Point Exceptions have been reported - 7,255,793,129 cycles # 2.976 GHz - 16,893,479,508 instructions # 2.33 insn per cycle - 2.438946558 seconds time elapsed + 7,216,847,131 cycles # 2.925 GHz + 16,891,846,951 instructions # 2.34 insn per cycle + 2.468502980 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1350) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039280066150E-002 Relative difference = 5.612189004572479e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.990768e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.128430e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.128430e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.924187e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.020326e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.020326e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.464869 sec +TOTAL : 2.522608 sec INFO: No Floating Point Exceptions have been reported - 7,151,311,767 cycles # 2.896 GHz - 13,635,278,053 instructions # 1.91 insn per cycle - 2.470013945 seconds time elapsed + 7,150,122,380 cycles # 2.829 GHz + 13,633,449,373 instructions # 1.91 insn per cycle + 2.528205937 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2061) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053220800939E-002 Relative difference = 2.5107486628541925e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.053885e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.294288e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.294288e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.976818e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.175866e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.175866e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270341e-06 ) GeV^0 -TOTAL : 2.422093 sec +TOTAL : 2.485267 sec INFO: No Floating Point Exceptions have been reported - 7,026,614,378 cycles # 2.896 GHz - 13,450,065,466 instructions # 1.91 insn per cycle - 2.427233834 seconds time elapsed + 7,047,642,186 cycles # 2.830 GHz + 13,442,931,038 instructions # 1.91 insn per cycle + 2.490839699 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1940) (512y: 4) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828053220800939E-002 Relative difference = 2.5107486628541925e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.692384e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.295789e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.295789e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.604837e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.103202e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.103202e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270342e-06 ) GeV^0 -TOTAL : 2.703935 sec +TOTAL : 2.790744 sec INFO: No Floating Point Exceptions have been reported - 6,330,095,085 cycles # 2.337 GHz - 13,164,073,111 instructions # 2.08 insn per cycle - 2.709192314 seconds time elapsed + 6,349,721,778 cycles # 2.272 GHz + 13,164,680,615 instructions # 2.07 insn per cycle + 2.796235299 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2033) (512y: 1) (512z: 1085) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282805e-02 Avg ME (F77/C++) = 1.2828052536860923E-002 Relative difference = 1.977588895209662e-07 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd0.txt index 9e3c17234..caa67d1a4 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:13:01 +DATE: 2024-09-15_11:10:00 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.431285e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.767514e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.933255e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.610039e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.567106e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.762593e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.658633 sec +TOTAL : 0.688497 sec INFO: No Floating Point Exceptions have been reported - 2,599,271,297 cycles # 2.919 GHz - 4,048,239,508 instructions # 1.56 insn per cycle - 0.950222116 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,665,329,968 cycles # 2.845 GHz + 4,055,682,627 instructions # 1.52 insn per cycle + 0.995154695 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 166 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039901590279E-002 Relative difference = 7.671454200650844e-09 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.034382e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.205392e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.205392e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.002881e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.168467e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.168467e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.484958 sec +TOTAL : 6.726627 sec INFO: No Floating Point Exceptions have been reported - 19,390,681,434 cycles # 2.989 GHz - 46,278,360,693 instructions # 2.39 insn per cycle - 6.489877171 seconds time elapsed + 19,724,365,546 cycles # 2.928 GHz + 46,388,641,620 instructions # 2.35 insn per cycle + 6.737968541 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 466) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039952548879E-002 Relative difference = 3.6990156841838714e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.649240e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.184330e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.184330e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.617185e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.143896e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.143896e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.219438 sec +TOTAL : 4.347629 sec INFO: No Floating Point Exceptions have been reported - 12,631,065,383 cycles # 2.991 GHz - 31,480,470,322 instructions # 2.49 insn per cycle - 4.224490541 seconds time elapsed + 12,771,945,524 cycles # 2.931 GHz + 31,577,972,239 instructions # 2.47 insn per cycle + 4.359278192 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1719) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039952548879E-002 Relative difference = 3.6990156841838714e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.008639e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.799566e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.799566e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.943978e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.720569e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.720569e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.536691 sec +TOTAL : 3.688531 sec INFO: No Floating Point Exceptions have been reported - 10,084,304,672 cycles # 2.849 GHz - 19,466,113,659 instructions # 1.93 insn per cycle - 3.541680504 seconds time elapsed + 10,322,037,008 cycles # 2.790 GHz + 19,570,801,424 instructions # 1.90 insn per cycle + 3.699996508 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2042) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.056481e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.878077e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.878077e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.986657e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.789520e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.789520e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.458920 sec +TOTAL : 3.618212 sec INFO: No Floating Point Exceptions have been reported - 9,912,300,699 cycles # 2.862 GHz - 19,210,733,007 instructions # 1.94 insn per cycle - 3.464025045 seconds time elapsed + 10,149,499,266 cycles # 2.797 GHz + 19,312,096,557 instructions # 1.90 insn per cycle + 3.629679706 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1785) (512y: 189) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.834847e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.462926e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.462926e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.777391e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.385382e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.385382e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.837142 sec +TOTAL : 3.992684 sec INFO: No Floating Point Exceptions have been reported - 8,397,548,989 cycles # 2.187 GHz - 15,057,354,786 instructions # 1.79 insn per cycle - 3.842236435 seconds time elapsed + 8,588,251,503 cycles # 2.146 GHz + 15,161,251,122 instructions # 1.77 insn per cycle + 4.003805537 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 954) (512y: 154) (512z: 1322) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 diff --git a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd1.txt index 248fe7bdc..ce1b16067 100644 --- a/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum' -DATE: 2024-09-01_23:13:31 +DATE: 2024-09-15_11:10:30 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.434537e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.765664e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.929797e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.695377e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.640031e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.828039e+08 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 0.657503 sec +TOTAL : 0.676129 sec INFO: No Floating Point Exceptions have been reported - 2,608,075,068 cycles # 2.928 GHz - 4,002,537,795 instructions # 1.53 insn per cycle - 0.948969404 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,632,225,960 cycles # 2.883 GHz + 4,132,384,248 instructions # 1.57 insn per cycle + 0.970493332 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 154 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.282804e-02 Avg ME (F77/GPU) = 1.2828039901590279E-002 Relative difference = 7.671454200650844e-09 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.043875e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.213372e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.213372e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.005676e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.176899e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.176899e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 6.427915 sec +TOTAL : 6.735465 sec INFO: No Floating Point Exceptions have been reported - 19,262,761,937 cycles # 2.996 GHz - 46,214,044,642 instructions # 2.40 insn per cycle - 6.432871980 seconds time elapsed + 19,720,225,593 cycles # 2.924 GHz + 46,326,489,596 instructions # 2.35 insn per cycle + 6.746197968 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 453) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039952548879E-002 Relative difference = 3.6990156841838714e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.660972e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.186103e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.186103e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.574820e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.144081e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.144081e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 4.195922 sec +TOTAL : 4.449866 sec INFO: No Floating Point Exceptions have been reported - 12,533,967,278 cycles # 2.984 GHz - 31,452,817,753 instructions # 2.51 insn per cycle - 4.200889036 seconds time elapsed + 13,065,779,841 cycles # 2.930 GHz + 31,555,443,434 instructions # 2.42 insn per cycle + 4.460852067 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1711) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039952548879E-002 Relative difference = 3.6990156841838714e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.945450e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.706622e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.706622e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.952135e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.730440e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.730440e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.643145 sec +TOTAL : 3.677079 sec INFO: No Floating Point Exceptions have been reported - 10,121,690,290 cycles # 2.776 GHz - 19,453,283,154 instructions # 1.92 insn per cycle - 3.648095738 seconds time elapsed + 10,320,566,663 cycles # 2.800 GHz + 19,557,785,526 instructions # 1.90 insn per cycle + 3.688245631 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2026) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.066814e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.889937e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.889937e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.981919e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.782784e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.782784e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.441077 sec +TOTAL : 3.626089 sec INFO: No Floating Point Exceptions have been reported - 9,892,482,908 cycles # 2.871 GHz - 19,285,621,568 instructions # 1.95 insn per cycle - 3.446134033 seconds time elapsed + 10,150,645,903 cycles # 2.793 GHz + 19,388,040,023 instructions # 1.91 insn per cycle + 3.637342012 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1779) (512y: 189) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 12 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_EPEM_MUPMUM_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.898057e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.568308e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.568308e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.806136e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.449559e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.449559e+06 ) sec^-1 MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0 -TOTAL : 3.718166 sec +TOTAL : 3.931921 sec INFO: No Floating Point Exceptions have been reported - 8,231,795,227 cycles # 2.212 GHz - 14,974,124,019 instructions # 1.82 insn per cycle - 3.723482499 seconds time elapsed + 8,442,748,276 cycles # 2.150 GHz + 15,068,523,446 instructions # 1.78 insn per cycle + 3.943167549 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 947) (512y: 156) (512z: 1306) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 2 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 2 channels { 1 : 256, 2 : 256 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.282804e-02 Avg ME (F77/C++) = 1.2828039951670679E-002 Relative difference = 3.767475112924841e-09 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0.txt index d2edd191e..aeadfaae6 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:14:01 +DATE: 2024-09-15_11:11:01 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.670147e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.437270e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.004291e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.391981e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.330443e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.949573e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.523890 sec +TOTAL : 0.534465 sec INFO: No Floating Point Exceptions have been reported - 2,178,385,782 cycles # 2.885 GHz - 3,182,588,432 instructions # 1.46 insn per cycle - 0.812064572 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,210,485,527 cycles # 2.869 GHz + 3,136,829,588 instructions # 1.42 insn per cycle + 0.828432932 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.858232e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.905852e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.905852e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.818281e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.865529e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.865529e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.747452 sec +TOTAL : 5.911600 sec INFO: No Floating Point Exceptions have been reported - 17,237,152,794 cycles # 2.997 GHz - 45,932,361,580 instructions # 2.66 insn per cycle - 5.752612178 seconds time elapsed + 17,389,649,504 cycles # 2.935 GHz + 46,036,709,188 instructions # 2.65 insn per cycle + 5.925127688 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.186119e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.349184e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.349184e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.165855e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.325075e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.325075e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.399306 sec +TOTAL : 3.453922 sec INFO: No Floating Point Exceptions have been reported - 10,043,894,289 cycles # 2.951 GHz - 27,839,601,349 instructions # 2.77 insn per cycle - 3.404666318 seconds time elapsed + 10,171,046,914 cycles # 2.936 GHz + 27,937,548,503 instructions # 2.75 insn per cycle + 3.465600263 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2531) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.942338e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.320449e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.320449e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.967598e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.358232e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.358232e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.228364 sec +TOTAL : 2.252729 sec INFO: No Floating Point Exceptions have been reported - 6,109,581,175 cycles # 2.736 GHz - 12,581,401,053 instructions # 2.06 insn per cycle - 2.233705562 seconds time elapsed + 6,219,848,194 cycles # 2.748 GHz + 12,677,070,824 instructions # 2.04 insn per cycle + 2.263945260 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2619) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.484110e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.946408e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.946408e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.478036e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.948706e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.948706e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.018536 sec +TOTAL : 2.055945 sec INFO: No Floating Point Exceptions have been reported - 5,570,191,475 cycles # 2.753 GHz - 12,019,013,229 instructions # 2.16 insn per cycle - 2.023911725 seconds time elapsed + 5,693,440,562 cycles # 2.756 GHz + 12,116,317,958 instructions # 2.13 insn per cycle + 2.067013514 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2357) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.594274e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.785812e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.785812e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.483396e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.667202e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.667202e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.024112 sec +TOTAL : 3.151048 sec INFO: No Floating Point Exceptions have been reported - 5,693,875,340 cycles # 1.880 GHz - 8,293,914,748 instructions # 1.46 insn per cycle - 3.029595102 seconds time elapsed + 5,836,401,977 cycles # 1.846 GHz + 8,391,475,751 instructions # 1.44 insn per cycle + 3.162234928 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1441) (512y: 122) (512z: 1802) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_bridge.txt index 23f45cdec..9022013b0 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:42:43 +DATE: 2024-09-15_11:46:12 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.493626e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.788449e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.788449e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.381047e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.782856e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.782856e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.815005 sec +TOTAL : 0.840023 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,127,275,476 cycles # 2.947 GHz - 4,836,149,999 instructions # 1.55 insn per cycle - 1.119465655 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge + 3,108,426,192 cycles # 2.861 GHz + 4,770,924,698 instructions # 1.53 insn per cycle + 1.146594198 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublocks*gputhreads=524288) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -79,35 +79,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.858044e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.905317e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.905317e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.806159e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.852377e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.852377e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.830025 sec +TOTAL : 6.067320 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 17,599,347,450 cycles # 3.016 GHz - 45,994,268,031 instructions # 2.61 insn per cycle - 5.836722741 seconds time elapsed + 17,856,813,573 cycles # 2.936 GHz + 46,243,571,751 instructions # 2.59 insn per cycle + 6.083398130 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -115,33 +115,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.211060e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.365706e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.365706e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.134236e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.289007e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.289007e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.451835 sec +TOTAL : 3.611222 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 10,389,093,510 cycles # 3.005 GHz - 28,024,409,034 instructions # 2.70 insn per cycle - 3.458495700 seconds time elapsed + 10,640,342,598 cycles # 2.934 GHz + 28,274,377,614 instructions # 2.66 insn per cycle + 3.627839941 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2531) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -149,33 +149,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.022670e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.402018e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.402018e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.918119e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.295386e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.295386e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.278536 sec +TOTAL : 2.398079 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,457,442,090 cycles # 2.827 GHz - 12,870,074,518 instructions # 1.99 insn per cycle - 2.285452391 seconds time elapsed + 6,685,318,792 cycles # 2.770 GHz + 13,122,453,026 instructions # 1.96 insn per cycle + 2.414568983 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2619) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -183,33 +183,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.538075e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.001427e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.001427e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.370026e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.821205e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.821205e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.080838 sec +TOTAL : 2.218649 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 5,931,949,770 cycles # 2.843 GHz - 12,306,854,953 instructions # 2.07 insn per cycle - 2.087528338 seconds time elapsed + 6,189,711,182 cycles # 2.770 GHz + 12,557,371,407 instructions # 2.03 insn per cycle + 2.235322482 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2357) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -217,33 +217,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.606488e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.794562e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.794562e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.469847e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.650575e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.650575e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.095535 sec +TOTAL : 3.290950 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,067,000,673 cycles # 1.956 GHz - 8,541,484,367 instructions # 1.41 insn per cycle - 3.102199651 seconds time elapsed + 6,320,487,640 cycles # 1.913 GHz + 8,791,643,966 instructions # 1.39 insn per cycle + 3.307886654 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1441) (512y: 122) (512z: 1802) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -251,8 +251,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_common.txt index d505b8769..85f95aac4 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:54:42 +DATE: 2024-09-15_11:58:30 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.236642e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.108245e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.774075e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.424217e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.466051e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.011391e+08 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 0.625400 sec +TOTAL : 0.646400 sec INFO: No Floating Point Exceptions have been reported - 2,500,275,084 cycles # 2.922 GHz - 3,660,372,041 instructions # 1.46 insn per cycle - 0.913293893 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common + 2,528,248,856 cycles # 2.879 GHz + 3,688,196,917 instructions # 1.46 insn per cycle + 0.934986871 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.860204e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.908027e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.908027e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.819736e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.867152e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.867152e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 5.803551 sec +TOTAL : 5.985044 sec INFO: No Floating Point Exceptions have been reported - 17,410,566,389 cycles # 2.998 GHz - 45,948,240,516 instructions # 2.64 insn per cycle - 5.809030601 seconds time elapsed + 17,600,111,411 cycles # 2.936 GHz + 46,124,554,790 instructions # 2.62 insn per cycle + 5.995774241 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.242345e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.401455e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.401455e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.168097e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.326675e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.326675e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 3.399393 sec +TOTAL : 3.533047 sec INFO: No Floating Point Exceptions have been reported - 10,226,528,939 cycles # 3.004 GHz - 27,838,493,655 instructions # 2.72 insn per cycle - 3.404881515 seconds time elapsed + 10,405,596,477 cycles # 2.937 GHz + 28,016,084,485 instructions # 2.69 insn per cycle + 3.543840924 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2531) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.089523e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.488778e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.488778e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.000915e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.392912e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.392912e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 2.227519 sec +TOTAL : 2.319991 sec INFO: No Floating Point Exceptions have been reported - 6,296,693,700 cycles # 2.821 GHz - 12,563,741,360 instructions # 2.00 insn per cycle - 2.232914857 seconds time elapsed + 6,443,899,577 cycles # 2.766 GHz + 12,743,367,354 instructions # 1.98 insn per cycle + 2.330731733 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2619) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.492330e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.954969e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.954969e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.453355e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.917864e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.917864e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 2.078395 sec +TOTAL : 2.148765 sec INFO: No Floating Point Exceptions have been reported - 5,760,797,019 cycles # 2.765 GHz - 11,965,976,847 instructions # 2.08 insn per cycle - 2.084185413 seconds time elapsed + 5,965,699,512 cycles # 2.764 GHz + 12,146,978,501 instructions # 2.04 insn per cycle + 2.159407986 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2357) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.621135e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.815003e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.815003e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.499391e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.683844e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.683844e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079401e+00 +- 3.402993e-03 ) GeV^0 -TOTAL : 3.061718 sec +TOTAL : 3.221377 sec INFO: No Floating Point Exceptions have been reported - 5,891,546,452 cycles # 1.922 GHz - 8,243,365,807 instructions # 1.40 insn per cycle - 3.067136953 seconds time elapsed + 6,080,803,082 cycles # 1.882 GHz + 8,423,087,351 instructions # 1.39 insn per cycle + 3.232264502 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1441) (512y: 122) (512z: 1802) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_curhst.txt index f1a7279f4..a207bf696 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:51:54 +DATE: 2024-09-15_11:55:37 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.273434e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.280412e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.968161e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.567312e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.455238e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.007252e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.562544 sec +TOTAL : 0.563061 sec INFO: No Floating Point Exceptions have been reported - 2,322,125,439 cycles # 2.928 GHz - 3,645,722,192 instructions # 1.57 insn per cycle - 0.850249349 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst + 2,285,403,688 cycles # 2.879 GHz + 3,587,140,832 instructions # 1.57 insn per cycle + 0.850548380 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.858859e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.905786e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.905786e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.818247e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.865618e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.865618e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.747389 sec +TOTAL : 5.910910 sec INFO: No Floating Point Exceptions have been reported - 17,237,233,259 cycles # 2.997 GHz - 45,935,224,991 instructions # 2.66 insn per cycle - 5.752803841 seconds time elapsed + 17,366,644,102 cycles # 2.933 GHz + 46,048,599,584 instructions # 2.65 insn per cycle + 5.921509733 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.234441e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.394817e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.394817e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.165029e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.323362e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.323362e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.347494 sec +TOTAL : 3.462860 sec INFO: No Floating Point Exceptions have been reported - 10,060,095,556 cycles # 3.001 GHz - 27,840,812,105 instructions # 2.77 insn per cycle - 3.352886847 seconds time elapsed + 10,189,100,613 cycles # 2.933 GHz + 27,958,354,355 instructions # 2.74 insn per cycle + 3.474989469 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2531) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.050411e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.453973e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.453973e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.979916e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.371493e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.371493e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.184644 sec +TOTAL : 2.251622 sec INFO: No Floating Point Exceptions have been reported - 6,160,511,677 cycles # 2.816 GHz - 12,582,281,977 instructions # 2.04 insn per cycle - 2.190146485 seconds time elapsed + 6,239,671,348 cycles # 2.759 GHz + 12,698,985,692 instructions # 2.04 insn per cycle + 2.262379977 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2619) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.619096e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.102203e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.102203e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.471204e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.935728e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.935728e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 1.971941 sec +TOTAL : 2.061624 sec INFO: No Floating Point Exceptions have been reported - 5,581,458,565 cycles # 2.824 GHz - 12,016,750,817 instructions # 2.15 insn per cycle - 1.977376660 seconds time elapsed + 5,721,552,525 cycles # 2.762 GHz + 12,134,935,244 instructions # 2.12 insn per cycle + 2.072280515 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2357) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.649577e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.841164e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.841164e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.500472e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.684328e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.684328e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.978936 sec +TOTAL : 3.142449 sec INFO: No Floating Point Exceptions have been reported - 5,694,372,557 cycles # 1.909 GHz - 8,293,954,373 instructions # 1.46 insn per cycle - 2.984356046 seconds time elapsed + 5,837,185,756 cycles # 1.853 GHz + 8,411,639,410 instructions # 1.44 insn per cycle + 3.153001098 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1441) (512y: 122) (512z: 1802) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_rmbhst.txt index c659726d0..fa08fbada 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,60 +11,60 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:49:10 +DATE: 2024-09-15_11:52:49 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.858498e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.254024e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.935929e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.726431e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.401767e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.003069e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.707983 sec +TOTAL : 0.719407 sec INFO: No Floating Point Exceptions have been reported - 2,759,086,933 cycles # 2.941 GHz - 4,352,636,424 instructions # 1.58 insn per cycle - 0.995067409 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst + 2,718,962,196 cycles # 2.853 GHz + 4,261,744,999 instructions # 1.57 insn per cycle + 1.009279183 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -72,33 +72,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.826998e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.873338e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.873338e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.804236e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.851320e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.851320e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.846045 sec +TOTAL : 5.958188 sec INFO: No Floating Point Exceptions have been reported - 17,230,561,081 cycles # 2.945 GHz - 45,931,993,548 instructions # 2.67 insn per cycle - 5.851455306 seconds time elapsed + 17,386,557,790 cycles # 2.923 GHz + 46,053,036,463 instructions # 2.65 insn per cycle + 5.968882862 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -106,31 +106,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.244950e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.403701e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.403701e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.150158e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.308857e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.308857e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.336054 sec +TOTAL : 3.477756 sec INFO: No Floating Point Exceptions have been reported - 10,036,104,723 cycles # 3.004 GHz - 27,841,427,493 instructions # 2.77 insn per cycle - 3.341549572 seconds time elapsed + 10,179,732,087 cycles # 2.919 GHz + 27,956,952,229 instructions # 2.75 insn per cycle + 3.488776572 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2531) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -138,31 +138,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.088493e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.483787e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.483787e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.931728e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.313640e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.313640e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.165858 sec +TOTAL : 2.272950 sec INFO: No Floating Point Exceptions have been reported - 6,085,227,169 cycles # 2.804 GHz - 12,581,161,598 instructions # 2.07 insn per cycle - 2.171236876 seconds time elapsed + 6,250,280,118 cycles # 2.738 GHz + 12,699,256,189 instructions # 2.03 insn per cycle + 2.283692354 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2619) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -170,31 +170,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.560737e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.029058e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.029058e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.454076e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.923276e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.923276e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 1.990270 sec +TOTAL : 2.069149 sec INFO: No Floating Point Exceptions have been reported - 5,638,832,491 cycles # 2.827 GHz - 12,018,376,967 instructions # 2.13 insn per cycle - 1.995707338 seconds time elapsed + 5,725,799,884 cycles # 2.754 GHz + 12,135,179,967 instructions # 2.12 insn per cycle + 2.079783939 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2357) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -202,31 +202,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.665545e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.859718e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.859718e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.414550e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.592343e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.592343e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.965370 sec +TOTAL : 3.218110 sec INFO: No Floating Point Exceptions have been reported - 5,714,700,961 cycles # 1.924 GHz - 8,293,609,502 instructions # 1.45 insn per cycle - 2.970791328 seconds time elapsed + 5,959,079,250 cycles # 1.847 GHz + 8,422,189,176 instructions # 1.41 insn per cycle + 3.228977501 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1441) (512y: 122) (512z: 1802) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -234,8 +234,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd1.txt index f09bf18ae..328467ef6 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:14:25 +DATE: 2024-09-15_11:11:27 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.636159e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.308317e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.889429e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.368553e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.328924e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.965685e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.522612 sec +TOTAL : 0.531897 sec INFO: No Floating Point Exceptions have been reported - 2,180,477,207 cycles # 2.895 GHz - 3,172,870,054 instructions # 1.46 insn per cycle - 0.810836216 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,204,349,816 cycles # 2.864 GHz + 3,169,634,690 instructions # 1.44 insn per cycle + 0.825649601 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 212 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.897784e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.948555e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.948555e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.870268e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.919754e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.919754e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.630375 sec +TOTAL : 5.735202 sec INFO: No Floating Point Exceptions have been reported - 16,757,601,134 cycles # 2.974 GHz - 44,924,975,083 instructions # 2.68 insn per cycle - 5.635488054 seconds time elapsed + 16,847,713,247 cycles # 2.933 GHz + 44,981,738,957 instructions # 2.67 insn per cycle + 5.744748484 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 567) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.395050e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.569829e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.569829e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.300705e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.473658e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.473658e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.193638 sec +TOTAL : 3.304655 sec INFO: No Floating Point Exceptions have been reported - 9,562,770,661 cycles # 2.990 GHz - 26,698,506,537 instructions # 2.79 insn per cycle - 3.198859598 seconds time elapsed + 9,659,083,497 cycles # 2.916 GHz + 26,749,720,361 instructions # 2.77 insn per cycle + 3.314062418 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2328) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.695250e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.026786e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.026786e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.583161e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.907950e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.907950e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.337651 sec +TOTAL : 2.415079 sec INFO: No Floating Point Exceptions have been reported - 6,614,817,603 cycles # 2.825 GHz - 14,119,225,912 instructions # 2.13 insn per cycle - 2.342792443 seconds time elapsed + 6,675,336,151 cycles # 2.753 GHz + 14,174,925,457 instructions # 2.12 insn per cycle + 2.425332683 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2710) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.825490e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.171719e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.171719e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.674600e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.017717e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.017717e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.278000 sec +TOTAL : 2.378233 sec INFO: No Floating Point Exceptions have been reported - 6,343,251,608 cycles # 2.779 GHz - 13,705,736,126 instructions # 2.16 insn per cycle - 2.283174093 seconds time elapsed + 6,574,155,578 cycles # 2.754 GHz + 13,789,180,928 instructions # 2.10 insn per cycle + 2.388565062 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2356) (512y: 297) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.324436e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.489374e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.489374e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.383516e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.554686e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.554686e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.260583 sec +TOTAL : 3.229855 sec INFO: No Floating Point Exceptions have been reported - 5,903,112,082 cycles # 1.808 GHz - 10,062,261,188 instructions # 1.70 insn per cycle - 3.265855245 seconds time elapsed + 5,994,389,719 cycles # 1.851 GHz + 10,123,629,860 instructions # 1.69 insn per cycle + 3.240029027 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1273) (512y: 208) (512z: 1988) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd0.txt index c4737ae00..2da881e2b 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:33:49 +DATE: 2024-09-15_11:35:31 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.441577e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.233882e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.865376e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.302471e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.316570e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.001729e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.524909 sec +TOTAL : 0.535501 sec INFO: No Floating Point Exceptions have been reported - 2,204,501,755 cycles # 2.906 GHz - 3,161,352,230 instructions # 1.43 insn per cycle - 0.815153775 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 + 2,215,078,191 cycles # 2.874 GHz + 3,154,679,095 instructions # 1.42 insn per cycle + 0.829146554 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.482527e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.569569e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.569569e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.351910e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.430033e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.430033e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 4.328984 sec +TOTAL : 4.571525 sec INFO: No Floating Point Exceptions have been reported - 13,010,239,001 cycles # 3.002 GHz - 34,342,983,400 instructions # 2.64 insn per cycle - 4.334635297 seconds time elapsed + 13,035,401,690 cycles # 2.848 GHz + 34,355,905,973 instructions # 2.64 insn per cycle + 4.578322526 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 665) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.026227e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.165110e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.165110e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.974205e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.110138e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.110138e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.570531 sec +TOTAL : 3.639722 sec INFO: No Floating Point Exceptions have been reported - 10,688,107,015 cycles # 2.990 GHz - 24,011,117,449 instructions # 2.25 insn per cycle - 3.576054169 seconds time elapsed + 10,720,308,622 cycles # 2.941 GHz + 24,027,850,859 instructions # 2.24 insn per cycle + 3.646936507 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.603793e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.926174e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.926174e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.622097e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.949479e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.949479e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.384762 sec +TOTAL : 2.385273 sec INFO: No Floating Point Exceptions have been reported - 6,599,795,120 cycles # 2.762 GHz - 12,349,103,691 instructions # 1.87 insn per cycle - 2.390301945 seconds time elapsed + 6,607,425,584 cycles # 2.762 GHz + 12,368,604,074 instructions # 1.87 insn per cycle + 2.392729796 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3103) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.982939e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.357856e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.357856e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.850394e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.302393e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.302393e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.211076 sec +TOTAL : 2.279711 sec INFO: No Floating Point Exceptions have been reported - 6,160,427,268 cycles # 2.780 GHz - 11,570,234,949 instructions # 1.88 insn per cycle - 2.216581669 seconds time elapsed + 6,291,615,830 cycles # 2.752 GHz + 11,595,311,145 instructions # 1.84 insn per cycle + 2.287442889 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2648) (512y: 239) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.869317e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.091369e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.091369e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.743982e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.952525e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.952525e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.815766 sec +TOTAL : 2.921108 sec INFO: No Floating Point Exceptions have been reported - 5,389,719,668 cycles # 1.911 GHz - 9,283,534,251 instructions # 1.72 insn per cycle - 2.821353617 seconds time elapsed + 5,423,773,794 cycles # 1.852 GHz + 9,310,782,229 instructions # 1.72 insn per cycle + 2.929084188 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2096) (512y: 282) (512z: 1955) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd1.txt index 4598d7e2e..86df224c9 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_d_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:34:12 +DATE: 2024-09-15_11:35:55 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.473262e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.369697e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.001580e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.255241e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.245059e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.949681e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.525400 sec +TOTAL : 0.533151 sec INFO: No Floating Point Exceptions have been reported - 2,217,363,075 cycles # 2.923 GHz - 3,200,444,976 instructions # 1.44 insn per cycle - 0.815931801 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 + 2,204,451,822 cycles # 2.864 GHz + 3,124,206,943 instructions # 1.42 insn per cycle + 0.826948420 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 212 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063388516822 Relative difference = 3.2588034143755247e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.621117e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.716737e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.716737e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.566402e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.659710e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.659710e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 4.105569 sec +TOTAL : 4.199423 sec INFO: No Floating Point Exceptions have been reported - 12,322,987,130 cycles # 2.998 GHz - 34,913,845,215 instructions # 2.83 insn per cycle - 4.110930955 seconds time elapsed + 12,339,181,649 cycles # 2.934 GHz + 34,922,451,175 instructions # 2.83 insn per cycle + 4.206438418 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 430) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515649 Relative difference = 3.258803992249869e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.044826e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.184646e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.184646e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.977481e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.113067e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.113067e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.549215 sec +TOTAL : 3.637534 sec INFO: No Floating Point Exceptions have been reported - 10,667,286,256 cycles # 3.002 GHz - 23,012,274,265 instructions # 2.16 insn per cycle - 3.554585973 seconds time elapsed + 10,710,920,290 cycles # 2.939 GHz + 23,032,620,692 instructions # 2.15 insn per cycle + 3.644897421 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2340) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388515654 Relative difference = 3.2588039900609506e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.959234e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.341805e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.341805e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.909385e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.279214e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.279214e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.219712 sec +TOTAL : 2.252873 sec INFO: No Floating Point Exceptions have been reported - 6,206,346,340 cycles # 2.790 GHz - 11,957,801,780 instructions # 1.93 insn per cycle - 2.225127509 seconds time elapsed + 6,212,002,997 cycles # 2.749 GHz + 11,978,645,016 instructions # 1.93 insn per cycle + 2.260347594 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2491) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.169842e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.570767e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.570767e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.039032e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.423530e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.423530e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.131713 sec +TOTAL : 2.196002 sec INFO: No Floating Point Exceptions have been reported - 6,032,167,736 cycles # 2.824 GHz - 11,128,490,395 instructions # 1.84 insn per cycle - 2.137129004 seconds time elapsed + 6,062,556,643 cycles # 2.753 GHz + 11,146,456,018 instructions # 1.84 insn per cycle + 2.203425956 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2103) (512y: 174) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.056148e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.296486e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.296486e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.871031e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.091641e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.091641e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.690977 sec +TOTAL : 2.826553 sec INFO: No Floating Point Exceptions have been reported - 5,188,865,221 cycles # 1.925 GHz - 9,022,420,854 instructions # 1.74 insn per cycle - 2.696419516 seconds time elapsed + 5,265,704,314 cycles # 1.859 GHz + 9,046,022,125 instructions # 1.72 insn per cycle + 2.834187629 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1632) (512y: 208) (512z: 1571) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063388516204 Relative difference = 3.2588037186351226e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0.txt index 43668d5a1..e1d11759a 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:14:50 +DATE: 2024-09-15_11:11:52 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.016549e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.793906e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.905869e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.179768e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.708203e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.827426e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086719e+00 +- 3.413389e-03 ) GeV^0 -TOTAL : 0.487274 sec +TOTAL : 0.491224 sec INFO: No Floating Point Exceptions have been reported - 1,997,739,441 cycles # 2.811 GHz - 2,897,236,768 instructions # 1.45 insn per cycle - 0.769495399 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,056,714,115 cycles # 2.865 GHz + 2,916,773,309 instructions # 1.42 insn per cycle + 0.776029796 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.882513e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.935230e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.935230e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.918838e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.972832e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.972832e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 5.656519 sec +TOTAL : 5.552302 sec INFO: No Floating Point Exceptions have been reported - 16,240,144,549 cycles # 2.870 GHz - 45,333,715,938 instructions # 2.79 insn per cycle - 5.661567866 seconds time elapsed + 16,247,282,670 cycles # 2.924 GHz + 45,328,928,537 instructions # 2.79 insn per cycle + 5.557963082 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.418761e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.747409e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.747409e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.529514e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.866293e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.866293e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.459987 sec +TOTAL : 2.402922 sec INFO: No Floating Point Exceptions have been reported - 7,053,646,042 cycles # 2.862 GHz - 17,771,434,741 instructions # 2.52 insn per cycle - 2.465198154 seconds time elapsed + 7,055,912,070 cycles # 2.931 GHz + 17,768,218,222 instructions # 2.52 insn per cycle + 2.408607319 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3133) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.065007e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.131343e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.131343e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.299822e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.410195e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.410195e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.386858 sec +TOTAL : 1.350007 sec INFO: No Floating Point Exceptions have been reported - 3,742,121,111 cycles # 2.690 GHz - 8,264,654,394 instructions # 2.21 insn per cycle - 1.392057287 seconds time elapsed + 3,747,874,250 cycles # 2.767 GHz + 8,260,976,747 instructions # 2.20 insn per cycle + 1.355686963 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3364) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.712893e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.953154e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.953154e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.794382e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.005480e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.005480e+06 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.290169 sec +TOTAL : 1.278305 sec INFO: No Floating Point Exceptions have been reported - 3,547,204,215 cycles # 2.739 GHz - 7,917,181,494 instructions # 2.23 insn per cycle - 1.295874973 seconds time elapsed + 3,550,706,297 cycles # 2.767 GHz + 7,915,681,558 instructions # 2.23 insn per cycle + 1.284036639 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3208) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.314722e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.941966e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.941966e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.489307e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.134354e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.134354e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.748569 sec +TOTAL : 1.705925 sec INFO: No Floating Point Exceptions have been reported - 3,258,838,954 cycles # 1.859 GHz - 6,097,393,995 instructions # 1.87 insn per cycle - 1.753998859 seconds time elapsed + 3,272,576,419 cycles # 1.913 GHz + 6,103,138,487 instructions # 1.86 insn per cycle + 1.712010321 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2249) (512y: 24) (512z: 2155) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_bridge.txt index af3512768..4785fec17 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:43:09 +DATE: 2024-09-15_11:46:39 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.996475e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.103004e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.103004e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.985126e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.401873e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.401873e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086805e+00 +- 3.414078e-03 ) GeV^0 -TOTAL : 0.679008 sec +TOTAL : 0.682896 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,647,282,815 cycles # 2.916 GHz - 4,083,441,957 instructions # 1.54 insn per cycle - 0.966781318 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge + 2,622,267,762 cycles # 2.874 GHz + 4,057,326,622 instructions # 1.55 insn per cycle + 0.970912293 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublocks*gputhreads=524288) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -79,35 +79,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.961039e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.017138e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.017138e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.900194e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.953379e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.953379e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 5.474034 sec +TOTAL : 5.681942 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 16,432,761,783 cycles # 2.999 GHz - 45,377,602,500 instructions # 2.76 insn per cycle - 5.480474769 seconds time elapsed + 16,671,667,536 cycles # 2.929 GHz + 45,497,192,820 instructions # 2.73 insn per cycle + 5.692941265 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -115,33 +115,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.583926e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.923485e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.923485e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.487658e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.829841e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.829841e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.417806 sec +TOTAL : 2.506047 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 7,259,616,163 cycles # 2.996 GHz - 18,052,508,494 instructions # 2.49 insn per cycle - 2.424027513 seconds time elapsed + 7,392,710,973 cycles # 2.938 GHz + 18,162,302,699 instructions # 2.46 insn per cycle + 2.517172183 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3133) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -149,33 +149,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.420996e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.554165e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.554165e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.160433e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.262111e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.262111e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.376482 sec +TOTAL : 1.454756 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,944,996,980 cycles # 2.854 GHz - 8,501,442,678 instructions # 2.15 insn per cycle - 1.382794301 seconds time elapsed + 4,077,667,192 cycles # 2.783 GHz + 8,611,395,195 instructions # 2.11 insn per cycle + 1.466232607 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3364) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -183,33 +183,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.851997e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.010518e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.010518e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.644244e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.901065e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.901065e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.316183 sec +TOTAL : 1.382676 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,756,474,273 cycles # 2.842 GHz - 8,156,395,844 instructions # 2.17 insn per cycle - 1.322500713 seconds time elapsed + 3,878,507,500 cycles # 2.784 GHz + 8,265,873,907 instructions # 2.13 insn per cycle + 1.393862906 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3208) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -217,33 +217,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=524288) Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.544940e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.196808e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.196808e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.387022e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.022226e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.022226e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.734787 sec +TOTAL : 1.814510 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,470,022,350 cycles # 1.994 GHz - 6,354,238,204 instructions # 1.83 insn per cycle - 1.741207745 seconds time elapsed + 3,594,832,163 cycles # 1.970 GHz + 6,462,220,806 instructions # 1.80 insn per cycle + 1.825958297 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2249) (512y: 24) (512z: 2155) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -251,8 +251,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_common.txt index daf3f6073..ff1a0d1a3 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:55:07 +DATE: 2024-09-15_11:58:55 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.105377e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.687892e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.803548e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.402978e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.823028e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.958083e+08 ) sec^-1 MeanMatrixElemValue = ( 2.079446e+00 +- 3.403306e-03 ) GeV^0 -TOTAL : 0.572824 sec +TOTAL : 0.595970 sec INFO: No Floating Point Exceptions have been reported - 2,316,864,231 cycles # 2.921 GHz - 3,396,488,753 instructions # 1.47 insn per cycle - 0.852389057 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common + 2,351,354,548 cycles # 2.876 GHz + 3,444,506,671 instructions # 1.46 insn per cycle + 0.875001238 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.963961e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.019337e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.019337e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.915967e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.970379e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.970379e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079573e+00 +- 3.404712e-03 ) GeV^0 -TOTAL : 5.478025 sec +TOTAL : 5.649395 sec INFO: No Floating Point Exceptions have been reported - 16,411,823,234 cycles # 2.994 GHz - 45,361,511,621 instructions # 2.76 insn per cycle - 5.483296816 seconds time elapsed + 16,580,294,518 cycles # 2.931 GHz + 45,471,304,380 instructions # 2.74 insn per cycle + 5.657307639 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.600554e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.940535e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.940535e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.539990e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.880360e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.880360e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079572e+00 +- 3.404712e-03 ) GeV^0 -TOTAL : 2.418365 sec +TOTAL : 2.485589 sec INFO: No Floating Point Exceptions have been reported - 7,218,096,486 cycles # 2.979 GHz - 17,782,873,843 instructions # 2.46 insn per cycle - 2.423530812 seconds time elapsed + 7,332,359,110 cycles # 2.941 GHz + 17,888,678,821 instructions # 2.44 insn per cycle + 2.493593708 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3133) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.543812e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.711869e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.711869e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.267444e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.414148e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.414148e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079550e+00 +- 3.404207e-03 ) GeV^0 -TOTAL : 1.365436 sec +TOTAL : 1.445011 sec INFO: No Floating Point Exceptions have been reported - 3,906,564,487 cycles # 2.852 GHz - 8,246,033,428 instructions # 2.11 insn per cycle - 1.370596175 seconds time elapsed + 4,026,136,405 cycles # 2.773 GHz + 8,355,233,205 instructions # 2.08 insn per cycle + 1.452615562 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3364) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.738190e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.991307e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.991307e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.729960e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.002290e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.002290e+06 ) sec^-1 MeanMatrixElemValue = ( 2.079550e+00 +- 3.404207e-03 ) GeV^0 -TOTAL : 1.342405 sec +TOTAL : 1.378766 sec INFO: No Floating Point Exceptions have been reported - 3,715,161,732 cycles # 2.758 GHz - 7,867,702,148 instructions # 2.12 insn per cycle - 1.347728919 seconds time elapsed + 3,842,420,700 cycles # 2.773 GHz + 7,976,068,469 instructions # 2.08 insn per cycle + 1.386498519 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3208) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.657423e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.354178e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.354178e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.464492e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.118413e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.118413e+05 ) sec^-1 MeanMatrixElemValue = ( 2.079550e+00 +- 3.404208e-03 ) GeV^0 -TOTAL : 1.720331 sec +TOTAL : 1.801449 sec INFO: No Floating Point Exceptions have been reported - 3,434,778,202 cycles # 1.991 GHz - 6,046,919,674 instructions # 1.76 insn per cycle - 1.725698557 seconds time elapsed + 3,544,493,993 cycles # 1.960 GHz + 6,155,712,678 instructions # 1.74 insn per cycle + 1.809068044 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2249) (512y: 24) (512z: 2155) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_curhst.txt index a26ce1355..d6446e740 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:52:19 +DATE: 2024-09-15_11:56:02 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.300334e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.753955e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.878936e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.563506e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.776392e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.890773e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086719e+00 +- 3.413389e-03 ) GeV^0 -TOTAL : 0.515714 sec +TOTAL : 0.519623 sec INFO: No Floating Point Exceptions have been reported - 2,131,743,033 cycles # 2.892 GHz - 3,363,258,452 instructions # 1.58 insn per cycle - 0.793874595 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst + 2,142,971,519 cycles # 2.865 GHz + 3,298,601,891 instructions # 1.54 insn per cycle + 0.804804703 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.955916e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.010652e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.010652e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.921389e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.976206e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.976206e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 5.445137 sec +TOTAL : 5.559284 sec INFO: No Floating Point Exceptions have been reported - 16,242,922,108 cycles # 2.981 GHz - 45,332,069,683 instructions # 2.79 insn per cycle - 5.450297847 seconds time elapsed + 16,314,564,993 cycles # 2.932 GHz + 45,379,598,894 instructions # 2.78 insn per cycle + 5.566847007 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.593016e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.934269e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.934269e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.507753e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.846242e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.846242e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.367261 sec +TOTAL : 2.429783 sec INFO: No Floating Point Exceptions have been reported - 7,054,204,460 cycles # 2.974 GHz - 17,770,139,491 instructions # 2.52 insn per cycle - 2.372459853 seconds time elapsed + 7,122,810,590 cycles # 2.924 GHz + 17,820,548,090 instructions # 2.50 insn per cycle + 2.437485624 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3133) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.502328e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.661035e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.661035e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.248249e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.390772e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.390772e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.317120 sec +TOTAL : 1.373977 sec INFO: No Floating Point Exceptions have been reported - 3,741,592,813 cycles # 2.831 GHz - 8,261,772,173 instructions # 2.21 insn per cycle - 1.322339821 seconds time elapsed + 3,800,696,374 cycles # 2.752 GHz + 8,311,474,483 instructions # 2.19 insn per cycle + 1.381547073 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3364) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.964572e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.026851e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.026851e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.515740e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.758099e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.758099e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.253784 sec +TOTAL : 1.334783 sec INFO: No Floating Point Exceptions have been reported - 3,555,905,791 cycles # 2.826 GHz - 7,915,891,992 instructions # 2.23 insn per cycle - 1.259045889 seconds time elapsed + 3,623,427,363 cycles # 2.701 GHz + 7,966,643,374 instructions # 2.20 insn per cycle + 1.342318524 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3208) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.676750e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.352514e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.352514e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.461308e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.125295e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.125295e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.655409 sec +TOTAL : 1.726295 sec INFO: No Floating Point Exceptions have been reported - 3,257,600,602 cycles # 1.963 GHz - 6,097,719,225 instructions # 1.87 insn per cycle - 1.660515865 seconds time elapsed + 3,316,188,727 cycles # 1.914 GHz + 6,146,469,798 instructions # 1.85 insn per cycle + 1.733694711 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2249) (512y: 24) (512z: 2155) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_rmbhst.txt index cd228c728..a7d3a3bca 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,60 +11,60 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:49:35 +DATE: 2024-09-15_11:53:15 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.610160e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.729460e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.851466e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.603732e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.769962e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.882903e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086805e+00 +- 3.414078e-03 ) GeV^0 -TOTAL : 0.621610 sec +TOTAL : 0.632677 sec INFO: No Floating Point Exceptions have been reported - 2,495,868,152 cycles # 2.929 GHz - 3,886,369,127 instructions # 1.56 insn per cycle - 0.908856599 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst + 2,459,588,784 cycles # 2.873 GHz + 3,830,411,115 instructions # 1.56 insn per cycle + 0.912203024 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -72,33 +72,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.971253e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.026799e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.026799e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.920423e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.975843e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.975843e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 5.403033 sec +TOTAL : 5.564298 sec INFO: No Floating Point Exceptions have been reported - 16,249,477,757 cycles # 3.005 GHz - 45,335,346,673 instructions # 2.79 insn per cycle - 5.408147099 seconds time elapsed + 16,322,815,770 cycles # 2.930 GHz + 45,379,862,622 instructions # 2.78 insn per cycle + 5.571986399 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -106,31 +106,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.620852e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.968419e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.968419e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.531426e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.870727e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.870727e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.355141 sec +TOTAL : 2.417527 sec INFO: No Floating Point Exceptions have been reported - 7,053,446,897 cycles # 2.989 GHz - 17,770,125,835 instructions # 2.52 insn per cycle - 2.360367399 seconds time elapsed + 7,119,927,533 cycles # 2.937 GHz + 17,819,194,741 instructions # 2.50 insn per cycle + 2.425172051 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3133) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -138,31 +138,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.504482e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.644248e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.644248e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.302342e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.447707e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.447707e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.317218 sec +TOTAL : 1.366211 sec INFO: No Floating Point Exceptions have been reported - 3,740,370,277 cycles # 2.830 GHz - 8,261,533,304 instructions # 2.21 insn per cycle - 1.322470933 seconds time elapsed + 3,809,953,710 cycles # 2.774 GHz + 8,311,255,796 instructions # 2.18 insn per cycle + 1.374030854 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3364) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -170,31 +170,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.002178e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.030213e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.030213e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.793036e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.010397e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.010397e+06 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.248992 sec +TOTAL : 1.299199 sec INFO: No Floating Point Exceptions have been reported - 3,542,544,565 cycles # 2.826 GHz - 7,916,798,793 instructions # 2.23 insn per cycle - 1.254257229 seconds time elapsed + 3,629,527,941 cycles # 2.777 GHz + 7,964,563,950 instructions # 2.19 insn per cycle + 1.308355970 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3208) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -202,31 +202,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.739256e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.427515e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.427515e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.490800e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.161305e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.161305e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.640887 sec +TOTAL : 1.720915 sec INFO: No Floating Point Exceptions have been reported - 3,256,631,314 cycles # 1.979 GHz - 6,096,520,142 instructions # 1.87 insn per cycle - 1.646153425 seconds time elapsed + 3,334,705,650 cycles # 1.929 GHz + 6,144,839,228 instructions # 1.84 insn per cycle + 1.729518385 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2249) (512y: 24) (512z: 2155) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -234,8 +234,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd1.txt index ed08ab638..1a7a19dcf 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:15:11 +DATE: 2024-09-15_11:12:13 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.789940e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.792429e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.906090e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.207213e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.745203e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.857795e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086719e+00 +- 3.413389e-03 ) GeV^0 -TOTAL : 0.489009 sec +TOTAL : 0.487469 sec INFO: No Floating Point Exceptions have been reported - 2,018,318,532 cycles # 2.827 GHz - 2,895,980,289 instructions # 1.43 insn per cycle - 0.772992983 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,053,225,612 cycles # 2.869 GHz + 2,963,841,312 instructions # 1.44 insn per cycle + 0.771871582 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 126 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.940323e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.995439e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.995439e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.964254e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.021824e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.021824e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 5.488792 sec +TOTAL : 5.438732 sec INFO: No Floating Point Exceptions have been reported - 15,940,533,363 cycles # 2.902 GHz - 44,444,792,927 instructions # 2.79 insn per cycle - 5.494044330 seconds time elapsed + 16,004,474,289 cycles # 2.939 GHz + 44,480,990,455 instructions # 2.78 insn per cycle + 5.447104045 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 536) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288198669441044 Relative difference = 6.558289825352968e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.239530e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.705587e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.705587e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.270854e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.739248e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.739248e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.087450 sec +TOTAL : 2.093047 sec INFO: No Floating Point Exceptions have been reported - 6,069,051,730 cycles # 2.901 GHz - 17,076,951,521 instructions # 2.81 insn per cycle - 2.092819349 seconds time elapsed + 6,146,902,561 cycles # 2.927 GHz + 17,124,330,277 instructions # 2.79 insn per cycle + 2.101358753 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2864) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193075684831 Relative difference = 1.515997647531052e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.981279e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.548807e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.548807e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.010634e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.590643e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.590643e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.838037 sec +TOTAL : 1.845256 sec INFO: No Floating Point Exceptions have been reported - 5,020,094,590 cycles # 2.724 GHz - 10,226,757,184 instructions # 2.04 insn per cycle - 1.843419915 seconds time elapsed + 5,092,053,198 cycles # 2.749 GHz + 10,266,716,383 instructions # 2.02 insn per cycle + 1.853336006 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3907) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.249511e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.851451e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.851451e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.078233e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.679535e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.679535e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.760706 sec +TOTAL : 1.828978 sec INFO: No Floating Point Exceptions have been reported - 4,966,480,857 cycles # 2.814 GHz - 9,996,514,844 instructions # 2.01 insn per cycle - 1.765809387 seconds time elapsed + 5,049,904,876 cycles # 2.749 GHz + 10,046,122,437 instructions # 1.99 insn per cycle + 1.837563375 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3806) (512y: 2) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181869545951 Relative difference = 9.214951531400725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.805571e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.146052e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.146052e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.649805e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.982891e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.982891e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 2.264482 sec +TOTAL : 2.359308 sec INFO: No Floating Point Exceptions have been reported - 4,363,518,057 cycles # 1.923 GHz - 8,444,795,066 instructions # 1.94 insn per cycle - 2.269675299 seconds time elapsed + 4,441,902,341 cycles # 1.877 GHz + 8,494,262,942 instructions # 1.91 insn per cycle + 2.367884804 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2746) (512y: 4) (512z: 2754) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183148950338 Relative difference = 1.5521108056421764e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd0.txt index d4756ce59..7bcb20b10 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:34:35 +DATE: 2024-09-15_11:36:18 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.603374e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.765581e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.882221e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.281805e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.729157e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.845967e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086719e+00 +- 3.413389e-03 ) GeV^0 -TOTAL : 0.485644 sec +TOTAL : 0.487987 sec INFO: No Floating Point Exceptions have been reported - 2,066,870,474 cycles # 2.910 GHz - 3,000,798,855 instructions # 1.45 insn per cycle - 0.768445011 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 + 2,055,281,728 cycles # 2.872 GHz + 2,956,266,509 instructions # 1.44 insn per cycle + 0.772297546 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.546441e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.640080e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.640080e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.496211e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.588163e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.588163e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 4.201218 sec +TOTAL : 4.287732 sec INFO: No Floating Point Exceptions have been reported - 12,581,623,324 cycles # 2.992 GHz - 34,609,638,297 instructions # 2.75 insn per cycle - 4.206417902 seconds time elapsed + 12,584,199,997 cycles # 2.932 GHz + 34,606,962,286 instructions # 2.75 insn per cycle + 4.293417398 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 683) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288199094356969 Relative difference = 4.463890496342449e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.413724e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.896525e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.896525e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.317872e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.783743e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.783743e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.021769 sec +TOTAL : 2.058410 sec INFO: No Floating Point Exceptions have been reported - 6,062,874,785 cycles # 2.992 GHz - 14,848,758,253 instructions # 2.45 insn per cycle - 2.026822059 seconds time elapsed + 6,058,288,486 cycles # 2.936 GHz + 14,847,536,122 instructions # 2.45 insn per cycle + 2.064093895 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2980) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193414453417 Relative difference = 1.6829758681196702e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.309646e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.143470e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.143470e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.131335e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.950373e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.950373e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.516599 sec +TOTAL : 1.556955 sec INFO: No Floating Point Exceptions have been reported - 4,292,704,034 cycles # 2.823 GHz - 9,054,713,499 instructions # 2.11 insn per cycle - 1.521729173 seconds time elapsed + 4,316,973,163 cycles # 2.764 GHz + 9,053,302,579 instructions # 2.10 insn per cycle + 1.562583378 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4460) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181974319741 Relative difference = 9.731379272303266e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.509425e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.388317e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.388317e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.308917e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.178890e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.178890e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.478807 sec +TOTAL : 1.521257 sec INFO: No Floating Point Exceptions have been reported - 4,198,253,929 cycles # 2.830 GHz - 8,663,551,193 instructions # 2.06 insn per cycle - 1.483957255 seconds time elapsed + 4,205,210,775 cycles # 2.756 GHz + 8,662,511,141 instructions # 2.06 insn per cycle + 1.526851661 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4225) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288181974319741 Relative difference = 9.731379272303266e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.598209e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.065067e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.065067e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.372555e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.809988e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.809988e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.957003 sec +TOTAL : 2.038768 sec INFO: No Floating Point Exceptions have been reported - 3,829,608,493 cycles # 1.953 GHz - 7,806,553,120 instructions # 2.04 insn per cycle - 1.962132869 seconds time elapsed + 3,837,026,814 cycles # 1.878 GHz + 7,805,330,859 instructions # 2.03 insn per cycle + 2.044464874 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4273) (512y: 0) (512z: 2558) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183246739209 Relative difference = 1.6003107281264138e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd1.txt index ae30e9c24..69afb6ef9 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_f_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:34:55 +DATE: 2024-09-15_11:36:38 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.609521e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.765362e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.882743e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.211144e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.722563e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.857000e+08 ) sec^-1 MeanMatrixElemValue = ( 2.086719e+00 +- 3.413389e-03 ) GeV^0 -TOTAL : 0.484090 sec +TOTAL : 0.487617 sec INFO: No Floating Point Exceptions have been reported - 2,069,775,597 cycles # 2.915 GHz - 2,991,357,430 instructions # 1.45 insn per cycle - 0.767321876 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 + 2,060,698,152 cycles # 2.879 GHz + 2,912,783,409 instructions # 1.41 insn per cycle + 0.772686787 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 126 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028811e+00 Avg ME (F77/GPU) = 2.0288499356247485 Relative difference = 1.9191351362116207e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.594738e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.692575e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.692575e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.666171e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.771083e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.771083e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086780e+00 +- 3.413794e-03 ) GeV^0 -TOTAL : 4.124478 sec +TOTAL : 4.019199 sec INFO: No Floating Point Exceptions have been reported - 11,853,777,518 cycles # 2.871 GHz - 35,078,486,896 instructions # 2.96 insn per cycle - 4.129581902 seconds time elapsed + 11,827,953,010 cycles # 2.940 GHz + 35,076,444,454 instructions # 2.97 insn per cycle + 4.024833106 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 453) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028820e+00 Avg ME (F77/C++) = 2.0288199094356969 Relative difference = 4.463890496342449e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.387597e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.876622e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.876622e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.415928e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.902704e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.902704e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086779e+00 +- 3.413793e-03 ) GeV^0 -TOTAL : 2.032118 sec +TOTAL : 2.023749 sec INFO: No Floating Point Exceptions have been reported - 5,954,220,246 cycles # 2.924 GHz - 14,471,125,804 instructions # 2.43 insn per cycle - 2.037354801 seconds time elapsed + 5,953,573,213 cycles # 2.935 GHz + 14,468,346,196 instructions # 2.43 insn per cycle + 2.029398775 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2559) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028819e+00 Avg ME (F77/C++) = 2.0288193583255634 Relative difference = 1.7661780742548925e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.547735e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.457816e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.457816e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.382613e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.271116e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.271116e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.473387 sec +TOTAL : 1.507601 sec INFO: No Floating Point Exceptions have been reported - 4,172,232,401 cycles # 2.823 GHz - 8,881,553,593 instructions # 2.13 insn per cycle - 1.478367886 seconds time elapsed + 4,170,609,924 cycles # 2.758 GHz + 8,881,070,721 instructions # 2.13 insn per cycle + 1.513291878 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3570) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288182104704902 Relative difference = 1.0374044905426431e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.564022e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.474971e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.474971e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.441367e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.356283e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.356283e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.470326 sec +TOTAL : 1.495607 sec INFO: No Floating Point Exceptions have been reported - 4,127,002,434 cycles # 2.799 GHz - 8,410,002,269 instructions # 2.04 insn per cycle - 1.475340782 seconds time elapsed + 4,129,531,699 cycles # 2.752 GHz + 8,406,651,679 instructions # 2.04 insn per cycle + 1.501280641 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3296) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288182104704902 Relative difference = 1.0374044905426431e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.698236e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.184991e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.184991e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.439343e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.891063e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.891063e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086810e+00 +- 3.414231e-03 ) GeV^0 -TOTAL : 1.924077 sec +TOTAL : 2.014863 sec INFO: No Floating Point Exceptions have been reported - 3,774,778,097 cycles # 1.958 GHz - 7,699,447,548 instructions # 2.04 insn per cycle - 1.929340998 seconds time elapsed + 3,794,076,081 cycles # 1.879 GHz + 7,699,347,303 instructions # 2.03 insn per cycle + 2.020593600 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3289) (512y: 0) (512z: 2110) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028818e+00 Avg ME (F77/C++) = 2.0288183204829693 Relative difference = 1.5796536184903122e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd0.txt index a3419d3eb..5fcfefd8b 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:15:33 +DATE: 2024-09-15_11:12:35 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.656233e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.473409e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.009011e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.360888e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.282446e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.948861e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.524071 sec +TOTAL : 0.535947 sec INFO: No Floating Point Exceptions have been reported - 2,200,106,592 cycles # 2.912 GHz - 3,136,630,811 instructions # 1.43 insn per cycle - 0.813499232 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,206,968,400 cycles # 2.863 GHz + 3,177,366,447 instructions # 1.44 insn per cycle + 0.829346124 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063423243874 Relative difference = 3.241686432649386e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.842313e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.889136e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.889136e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.801369e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.847904e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.847904e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.797564 sec +TOTAL : 5.967015 sec INFO: No Floating Point Exceptions have been reported - 17,380,525,335 cycles # 2.996 GHz - 46,085,182,385 instructions # 2.65 insn per cycle - 5.802980374 seconds time elapsed + 17,524,709,788 cycles # 2.932 GHz + 46,191,860,900 instructions # 2.64 insn per cycle + 5.978935443 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 617) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063903750300 Relative difference = 3.0048445715164216e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.264315e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.428282e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.428282e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.140467e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.299172e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.299172e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.317159 sec +TOTAL : 3.487825 sec INFO: No Floating Point Exceptions have been reported - 9,927,217,134 cycles # 2.989 GHz - 27,592,170,928 instructions # 2.78 insn per cycle - 3.322556315 seconds time elapsed + 10,261,674,067 cycles # 2.934 GHz + 27,722,537,189 instructions # 2.70 insn per cycle + 3.498978005 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2582) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063903750300 Relative difference = 3.0048445715164216e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.084318e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.477386e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.477386e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.032137e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.431710e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.431710e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.167284 sec +TOTAL : 2.231910 sec INFO: No Floating Point Exceptions have been reported - 6,096,775,135 cycles # 2.807 GHz - 12,483,393,435 instructions # 2.05 insn per cycle - 2.172749966 seconds time elapsed + 6,175,976,175 cycles # 2.753 GHz + 12,601,670,185 instructions # 2.04 insn per cycle + 2.244594220 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2774) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.317310e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.753244e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.753244e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.534616e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.015525e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.015525e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.077970 sec +TOTAL : 2.042072 sec INFO: No Floating Point Exceptions have been reported - 5,527,641,053 cycles # 2.654 GHz - 11,920,275,101 instructions # 2.16 insn per cycle - 2.083291823 seconds time elapsed + 5,669,805,165 cycles # 2.764 GHz + 12,036,562,183 instructions # 2.12 insn per cycle + 2.054181107 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2519) (512y: 146) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.734122e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.938328e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.938328e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.587962e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.783361e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.783361e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.911727 sec +TOTAL : 3.070999 sec INFO: No Floating Point Exceptions have been reported - 5,583,846,989 cycles # 1.915 GHz - 8,109,763,701 instructions # 1.45 insn per cycle - 2.917087683 seconds time elapsed + 5,754,052,644 cycles # 1.867 GHz + 8,225,264,257 instructions # 1.43 insn per cycle + 3.082911381 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1671) (512y: 126) (512z: 1863) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 diff --git a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd1.txt index 245c1b9aa..f3ccad174 100644 --- a/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:15:57 +DATE: 2024-09-15_11:13:00 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.642987e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.413319e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.000860e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.403841e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.350229e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.960040e+07 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 0.521821 sec +TOTAL : 0.532145 sec INFO: No Floating Point Exceptions have been reported - 2,190,325,490 cycles # 2.907 GHz - 3,184,963,858 instructions # 1.45 insn per cycle - 0.810757695 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,202,225,096 cycles # 2.860 GHz + 3,140,327,784 instructions # 1.43 insn per cycle + 0.826897706 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 212 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.028807e+00 Avg ME (F77/GPU) = 2.0288063423243874 Relative difference = 3.241686432649386e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.867143e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.915636e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.915636e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.849779e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.898891e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.898891e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 5.722177 sec +TOTAL : 5.812131 sec INFO: No Floating Point Exceptions have been reported - 16,937,691,218 cycles # 2.958 GHz - 45,108,922,900 instructions # 2.66 insn per cycle - 5.727585042 seconds time elapsed + 17,080,273,912 cycles # 2.934 GHz + 45,215,696,703 instructions # 2.65 insn per cycle + 5.823642020 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 568) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063903750300 Relative difference = 3.0048445715164216e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.410851e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.588061e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.588061e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.353337e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.532203e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.532203e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 3.179584 sec +TOTAL : 3.272970 sec INFO: No Floating Point Exceptions have been reported - 9,489,177,146 cycles # 2.981 GHz - 26,245,079,944 instructions # 2.77 insn per cycle - 3.185047895 seconds time elapsed + 9,622,203,648 cycles # 2.930 GHz + 26,352,115,115 instructions # 2.74 insn per cycle + 3.284795843 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2386) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288063903750300 Relative difference = 3.0048445715164216e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.580524e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.899812e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.899812e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.499939e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.814164e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.814164e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.394558 sec +TOTAL : 2.448542 sec INFO: No Floating Point Exceptions have been reported - 6,736,073,752 cycles # 2.808 GHz - 14,030,605,615 instructions # 2.08 insn per cycle - 2.400088375 seconds time elapsed + 6,760,703,277 cycles # 2.754 GHz + 14,051,302,777 instructions # 2.08 insn per cycle + 2.455916079 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2896) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.807671e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.164109e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.164109e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.725371e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.062901e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.062901e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.285657 sec +TOTAL : 2.336085 sec INFO: No Floating Point Exceptions have been reported - 6,414,671,963 cycles # 2.801 GHz - 13,521,130,801 instructions # 2.11 insn per cycle - 2.290985773 seconds time elapsed + 6,433,871,158 cycles # 2.746 GHz + 13,544,684,713 instructions # 2.11 insn per cycle + 2.343643276 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2535) (512y: 302) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.674213e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.870504e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.870504e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.546154e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.730746e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.730746e+05 ) sec^-1 MeanMatrixElemValue = ( 2.086689e+00 +- 3.413217e-03 ) GeV^0 -TOTAL : 2.959862 sec +TOTAL : 3.074398 sec INFO: No Floating Point Exceptions have been reported - 5,588,271,185 cycles # 1.885 GHz - 9,207,541,120 instructions # 1.65 insn per cycle - 2.965215793 seconds time elapsed + 5,684,367,008 cycles # 1.845 GHz + 9,231,965,840 instructions # 1.62 insn per cycle + 3.081687192 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1456) (512y: 212) (512z: 2060) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.028807e+00 Avg ME (F77/C++) = 2.0288064057068964 Relative difference = 2.9292737240031234e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0.txt index 570203dc1..0fe4cfc92 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:16:22 +DATE: 2024-09-15_11:13:25 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.798374e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.983326e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.078543e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.646703e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.903323e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.008440e+06 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 0.470552 sec +TOTAL : 0.472515 sec INFO: No Floating Point Exceptions have been reported - 1,997,326,811 cycles # 2.908 GHz - 2,877,302,032 instructions # 1.44 insn per cycle - 0.743546221 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,976,395,629 cycles # 2.864 GHz + 2,853,369,004 instructions # 1.44 insn per cycle + 0.746437756 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.058137e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.233632e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.243435e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.044065e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.229313e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.240372e+07 ) sec^-1 MeanMatrixElemValue = ( 6.734461e+02 +- 4.775415e+02 ) GeV^-2 -TOTAL : 0.606392 sec +TOTAL : 0.613454 sec INFO: No Floating Point Exceptions have been reported - 2,483,568,255 cycles # 2.922 GHz - 3,806,899,478 instructions # 1.53 insn per cycle - 0.908657999 seconds time elapsed + 2,457,306,952 cycles # 2.873 GHz + 3,760,458,763 instructions # 1.53 insn per cycle + 0.914581816 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.413122e+00 Avg ME (F77/GPU) = 1.4131213684418649 Relative difference = 4.469239988637851e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.474741e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.486951e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.486951e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.423163e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.435086e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.435086e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 6.640929 sec +TOTAL : 6.782254 sec INFO: No Floating Point Exceptions have been reported - 19,899,191,669 cycles # 2.995 GHz - 59,914,426,502 instructions # 3.01 insn per cycle - 6.645138273 seconds time elapsed + 19,933,068,888 cycles # 2.938 GHz + 59,910,639,029 instructions # 3.01 insn per cycle + 6.786428407 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1199) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.659881e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.702510e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.702510e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.574256e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.615519e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.615519e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 3.535409 sec +TOTAL : 3.601510 sec INFO: No Floating Point Exceptions have been reported - 10,570,379,022 cycles # 2.987 GHz - 31,084,508,228 instructions # 2.94 insn per cycle - 3.539526407 seconds time elapsed + 10,564,249,920 cycles # 2.931 GHz + 31,083,049,027 instructions # 2.94 insn per cycle + 3.605720194 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5221) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.311038e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.477508e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.477508e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.109445e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.271688e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.271688e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.779040 sec +TOTAL : 1.818340 sec INFO: No Floating Point Exceptions have been reported - 4,998,241,265 cycles # 2.804 GHz - 11,405,241,402 instructions # 2.28 insn per cycle - 1.783292570 seconds time elapsed + 4,995,758,651 cycles # 2.742 GHz + 11,404,411,821 instructions # 2.28 insn per cycle + 1.822613950 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4642) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.053479e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.074459e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.074459e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.031962e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.052518e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.052518e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.574748 sec +TOTAL : 1.607425 sec INFO: No Floating Point Exceptions have been reported - 4,439,382,728 cycles # 2.813 GHz - 10,663,698,368 instructions # 2.40 insn per cycle - 1.578969286 seconds time elapsed + 4,440,179,427 cycles # 2.756 GHz + 10,663,032,994 instructions # 2.40 insn per cycle + 1.611644858 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4378) (512y: 91) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.352968e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.457289e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.457289e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.095641e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.193407e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.193407e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 2.250021 sec +TOTAL : 2.331432 sec INFO: No Floating Point Exceptions have been reported - 4,132,805,814 cycles # 1.834 GHz - 5,966,681,608 instructions # 1.44 insn per cycle - 2.254297849 seconds time elapsed + 4,128,663,715 cycles # 1.768 GHz + 5,965,561,050 instructions # 1.44 insn per cycle + 2.335809030 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1617) (512y: 95) (512z: 3577) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416484 Relative difference = 4.469241520660492e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0_bridge.txt index 2c341e188..555f99fae 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:43:30 +DATE: 2024-09-15_11:47:00 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.550752e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.221480e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.221480e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.462205e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.092748e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.092748e+06 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 0.496080 sec +TOTAL : 0.504368 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,067,450,792 cycles # 2.916 GHz - 3,137,465,781 instructions # 1.52 insn per cycle - 0.766248980 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 2,053,925,551 cycles # 2.862 GHz + 3,120,835,610 instructions # 1.52 insn per cycle + 0.775288198 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.695395e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.206740e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.206740e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.695563e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.383097e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.383097e+06 ) sec^-1 MeanMatrixElemValue = ( 6.734461e+02 +- 4.775415e+02 ) GeV^-2 -TOTAL : 0.824513 sec +TOTAL : 0.834031 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,173,134,566 cycles # 2.947 GHz - 5,085,043,151 instructions # 1.60 insn per cycle - 1.134769459 seconds time elapsed + 3,122,984,951 cycles # 2.884 GHz + 5,028,895,726 instructions # 1.61 insn per cycle + 1.144542739 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.413122e+00 Avg ME (F77/GPU) = 1.4131213684418649 Relative difference = 4.469239988637851e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.485342e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.497625e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.497625e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.420974e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.433351e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.433351e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 6.619749 sec +TOTAL : 6.797187 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 19,931,458,281 cycles # 3.010 GHz - 59,921,540,931 instructions # 3.01 insn per cycle - 6.624128046 seconds time elapsed + 19,924,578,475 cycles # 2.930 GHz + 59,919,807,490 instructions # 3.01 insn per cycle + 6.801426045 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1199) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.696388e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.739462e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.739462e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.519993e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.562146e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.562146e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 3.515800 sec +TOTAL : 3.653302 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 10,606,854,369 cycles # 3.014 GHz - 31,134,291,194 instructions # 2.94 insn per cycle - 3.520321812 seconds time elapsed + 10,746,732,815 cycles # 2.939 GHz + 31,134,499,346 instructions # 2.90 insn per cycle + 3.657616586 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5221) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.249974e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.417505e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.417505e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.065515e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.233179e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.233179e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.799007 sec +TOTAL : 1.835810 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 5,036,417,695 cycles # 2.794 GHz - 11,456,150,189 instructions # 2.27 insn per cycle - 1.803522033 seconds time elapsed + 5,036,150,788 cycles # 2.739 GHz + 11,457,434,104 instructions # 2.28 insn per cycle + 1.839969686 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4642) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.043850e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.065311e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.065311e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.012086e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.033024e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.033024e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.596740 sec +TOTAL : 1.647583 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,500,129,968 cycles # 2.812 GHz - 10,714,925,901 instructions # 2.38 insn per cycle - 1.601086866 seconds time elapsed + 4,499,476,819 cycles # 2.725 GHz + 10,716,818,624 instructions # 2.38 insn per cycle + 1.651828196 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4378) (512y: 91) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.384293e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.494992e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.494992e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.046506e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.146814e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.146814e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 2.248261 sec +TOTAL : 2.355729 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,170,685,810 cycles # 1.852 GHz - 6,006,473,100 instructions # 1.44 insn per cycle - 2.252706319 seconds time elapsed + 4,171,753,505 cycles # 1.769 GHz + 6,006,835,350 instructions # 1.44 insn per cycle + 2.359914843 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1617) (512y: 95) (512z: 3577) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416484 Relative difference = 4.469241520660492e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd1.txt index 3fb3a47ab..df418c0c5 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:16:48 +DATE: 2024-09-15_11:13:51 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.834088e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.998800e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.096289e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.819441e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.940165e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.036270e+06 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 0.471420 sec +TOTAL : 0.473171 sec INFO: No Floating Point Exceptions have been reported - 1,961,056,023 cycles # 2.850 GHz - 2,802,491,151 instructions # 1.43 insn per cycle - 0.745710565 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,973,905,564 cycles # 2.864 GHz + 2,835,389,936 instructions # 1.44 insn per cycle + 0.747859769 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.046967e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.218286e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.227874e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.045923e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.239053e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.249723e+07 ) sec^-1 MeanMatrixElemValue = ( 6.734461e+02 +- 4.775415e+02 ) GeV^-2 -TOTAL : 0.603989 sec +TOTAL : 0.613723 sec INFO: No Floating Point Exceptions have been reported - 2,497,495,736 cycles # 2.934 GHz - 3,810,103,118 instructions # 1.53 insn per cycle - 0.911018204 seconds time elapsed + 2,468,512,324 cycles # 2.879 GHz + 3,722,507,305 instructions # 1.51 insn per cycle + 0.915283019 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.413122e+00 Avg ME (F77/GPU) = 1.4131213684418649 Relative difference = 4.469239988637851e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.451702e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.463867e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.463867e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.416240e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.428350e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.428350e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 6.703085 sec +TOTAL : 6.802073 sec INFO: No Floating Point Exceptions have been reported - 19,927,403,339 cycles # 2.972 GHz - 60,128,261,455 instructions # 3.02 insn per cycle - 6.707279948 seconds time elapsed + 19,919,234,926 cycles # 2.929 GHz + 60,126,857,831 instructions # 3.02 insn per cycle + 6.806341598 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1322) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.705461e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.749260e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.749260e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.628115e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.671006e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.671006e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 3.501187 sec +TOTAL : 3.560395 sec INFO: No Floating Point Exceptions have been reported - 10,472,673,137 cycles # 2.988 GHz - 30,685,134,556 instructions # 2.93 insn per cycle - 3.505272548 seconds time elapsed + 10,470,027,689 cycles # 2.938 GHz + 30,685,175,745 instructions # 2.93 insn per cycle + 3.564357324 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5047) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684432433 Relative difference = 4.46923023397472e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.078604e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.240538e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.240538e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.858005e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.013532e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.013532e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.823923 sec +TOTAL : 1.870006 sec INFO: No Floating Point Exceptions have been reported - 5,123,559,158 cycles # 2.804 GHz - 11,838,671,516 instructions # 2.31 insn per cycle - 1.828124881 seconds time elapsed + 5,129,037,452 cycles # 2.738 GHz + 11,838,972,708 instructions # 2.31 insn per cycle + 1.873874088 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4748) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.843118e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.002821e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.002821e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.652883e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.834044e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.834044e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.683810 sec +TOTAL : 1.717936 sec INFO: No Floating Point Exceptions have been reported - 4,722,608,139 cycles # 2.799 GHz - 11,163,576,715 instructions # 2.36 insn per cycle - 1.687961258 seconds time elapsed + 4,726,163,144 cycles # 2.747 GHz + 11,165,051,323 instructions # 2.36 insn per cycle + 1.721718897 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4403) (512y: 245) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416466 Relative difference = 4.469241533230934e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.277733e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.387064e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.387064e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.029308e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.126499e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.126499e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 2.272861 sec +TOTAL : 2.353551 sec INFO: No Floating Point Exceptions have been reported - 4,161,049,275 cycles # 1.828 GHz - 6,218,241,048 instructions # 1.49 insn per cycle - 2.277009938 seconds time elapsed + 4,165,348,623 cycles # 1.768 GHz + 6,220,012,480 instructions # 1.49 insn per cycle + 2.357450464 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1513) (512y: 140) (512z: 3679) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213684416484 Relative difference = 4.469241520660492e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0.txt index 34c4be0b1..0344b19ae 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:17:13 +DATE: 2024-09-15_11:14:17 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.699848e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.021832e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.054206e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.690436e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.002102e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.037933e+07 ) sec^-1 MeanMatrixElemValue = ( 1.008472e+02 +- 5.002447e+01 ) GeV^-2 -TOTAL : 0.455899 sec +TOTAL : 0.455498 sec INFO: No Floating Point Exceptions have been reported - 1,955,913,787 cycles # 2.919 GHz - 2,787,706,714 instructions # 1.43 insn per cycle - 0.727968230 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,928,242,310 cycles # 2.870 GHz + 2,746,045,826 instructions # 1.42 insn per cycle + 0.728814382 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 226 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.759047e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.411217e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.451705e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.680469e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.378510e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.424836e+07 ) sec^-1 MeanMatrixElemValue = ( 6.630097e+02 +- 4.770717e+02 ) GeV^-2 -TOTAL : 0.502101 sec +TOTAL : 0.509889 sec INFO: No Floating Point Exceptions have been reported - 2,122,727,370 cycles # 2.916 GHz - 3,075,859,437 instructions # 1.45 insn per cycle - 0.785300798 seconds time elapsed + 2,121,031,452 cycles # 2.862 GHz + 3,036,959,694 instructions # 1.43 insn per cycle + 0.800065199 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.412607e+00 Avg ME (F77/GPU) = 1.4132214305330990 Relative difference = 0.0004349621183379836 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.554989e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.568017e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.568017e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.504687e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.517708e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.517708e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 6.430950 sec +TOTAL : 6.560247 sec INFO: No Floating Point Exceptions have been reported - 19,259,058,983 cycles # 2.994 GHz - 59,617,547,503 instructions # 3.10 insn per cycle - 6.434961928 seconds time elapsed + 19,257,464,373 cycles # 2.934 GHz + 59,612,594,917 instructions # 3.10 insn per cycle + 6.564375492 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 959) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129949096991936 Relative difference = 6.390737857384068e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.187345e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.324546e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.324546e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.084277e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.218488e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.218488e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 2.018757 sec +TOTAL : 2.043801 sec INFO: No Floating Point Exceptions have been reported - 6,013,596,656 cycles # 2.974 GHz - 17,061,733,957 instructions # 2.84 insn per cycle - 2.022888104 seconds time elapsed + 6,009,096,977 cycles # 2.936 GHz + 17,060,655,087 instructions # 2.84 insn per cycle + 2.047534449 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5856) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129954647353316 Relative difference = 3.2890090308261873e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.775699e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.837851e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.837851e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.741509e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.801920e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.801920e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 0.940369 sec +TOTAL : 0.958794 sec INFO: No Floating Point Exceptions have been reported - 2,635,402,093 cycles # 2.792 GHz - 6,187,325,534 instructions # 2.35 insn per cycle - 0.944440901 seconds time elapsed + 2,632,796,186 cycles # 2.737 GHz + 6,187,347,650 instructions # 2.35 insn per cycle + 0.962496439 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 5105) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.922412e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.996476e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.996476e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.912269e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.986419e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.986419e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 0.870203 sec +TOTAL : 0.875039 sec INFO: No Floating Point Exceptions have been reported - 2,409,835,521 cycles # 2.759 GHz - 5,791,929,833 instructions # 2.40 insn per cycle - 0.874296773 seconds time elapsed + 2,407,469,182 cycles # 2.742 GHz + 5,790,784,602 instructions # 2.41 insn per cycle + 0.878768885 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4908) (512y: 36) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.493996e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.538601e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.538601e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.443174e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.485583e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.485583e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008856e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 1.116135 sec +TOTAL : 1.155478 sec INFO: No Floating Point Exceptions have been reported - 2,074,614,881 cycles # 1.853 GHz - 3,391,488,863 instructions # 1.63 insn per cycle - 1.120258678 seconds time elapsed + 2,073,615,836 cycles # 1.790 GHz + 3,391,178,624 instructions # 1.64 insn per cycle + 1.159306518 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2235) (512y: 39) (512z: 3789) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413316e+00 Avg ME (F77/C++) = 1.4133164033579249 Relative difference = 2.85398258307829e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0_bridge.txt index c0e91bec2..93fdf05be 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:43:55 +DATE: 2024-09-15_11:47:26 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.587121e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.558472e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.558472e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.480682e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.545762e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.545762e+07 ) sec^-1 MeanMatrixElemValue = ( 1.009071e+02 +- 5.002295e+01 ) GeV^-2 -TOTAL : 0.464282 sec +TOTAL : 0.469335 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,970,383,464 cycles # 2.910 GHz - 2,905,584,118 instructions # 1.47 insn per cycle - 0.733921324 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 1,971,009,268 cycles # 2.861 GHz + 2,878,621,667 instructions # 1.46 insn per cycle + 0.747088963 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 226 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.517059e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.199084e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.199084e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.503732e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.296845e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.296845e+07 ) sec^-1 MeanMatrixElemValue = ( 6.737499e+02 +- 4.776369e+02 ) GeV^-2 -TOTAL : 0.648992 sec +TOTAL : 0.653804 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,614,509,104 cycles # 2.934 GHz - 3,983,626,905 instructions # 1.52 insn per cycle - 0.949135243 seconds time elapsed + 2,546,264,462 cycles # 2.875 GHz + 3,884,000,523 instructions # 1.53 insn per cycle + 0.944357505 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.412607e+00 Avg ME (F77/GPU) = 1.4132214305330990 Relative difference = 0.0004349621183379836 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.569854e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.583003e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.583003e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.503119e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.516211e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.516211e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 6.397429 sec +TOTAL : 6.568401 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 19,269,183,636 cycles # 3.011 GHz - 59,618,162,881 instructions # 3.09 insn per cycle - 6.401657275 seconds time elapsed + 19,288,292,034 cycles # 2.936 GHz + 59,615,397,281 instructions # 3.09 insn per cycle + 6.572330246 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 959) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129949096991936 Relative difference = 6.390737857384068e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.278035e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.418496e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.418496e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.074244e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.211619e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.211619e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 2.000831 sec +TOTAL : 2.051717 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,033,592,364 cycles # 3.010 GHz - 17,110,022,408 instructions # 2.84 insn per cycle - 2.004963711 seconds time elapsed + 6,032,564,255 cycles # 2.936 GHz + 17,108,905,426 instructions # 2.84 insn per cycle + 2.055577630 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5856) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129954647353316 Relative difference = 3.2890090308261873e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.785493e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.848445e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.848445e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.735664e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.796597e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.796597e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 0.939049 sec +TOTAL : 0.965943 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,652,412,872 cycles # 2.814 GHz - 6,224,549,306 instructions # 2.35 insn per cycle - 0.943195146 seconds time elapsed + 2,652,269,080 cycles # 2.742 GHz + 6,224,274,753 instructions # 2.35 insn per cycle + 0.969710233 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 5105) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.876448e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.951702e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.951702e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.901208e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.974602e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.974602e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 0.896445 sec +TOTAL : 0.883566 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,434,305,262 cycles # 2.705 GHz - 5,828,516,984 instructions # 2.39 insn per cycle - 0.900793892 seconds time elapsed + 2,424,412,243 cycles # 2.734 GHz + 5,827,930,388 instructions # 2.40 insn per cycle + 0.887425140 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4908) (512y: 36) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.434857e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.477996e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.477996e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.438672e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.481527e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.481527e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008856e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 1.167264 sec +TOTAL : 1.163548 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,096,069,854 cycles # 1.790 GHz - 3,433,044,253 instructions # 1.64 insn per cycle - 1.171777259 seconds time elapsed + 2,093,109,210 cycles # 1.794 GHz + 3,432,132,802 instructions # 1.64 insn per cycle + 1.167531871 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2235) (512y: 39) (512z: 3789) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413316e+00 Avg ME (F77/C++) = 1.4133164033579249 Relative difference = 2.85398258307829e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd1.txt index ae4211ca1..04fc107fb 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:17:34 +DATE: 2024-09-15_11:14:38 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.749046e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.097285e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.132508e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.693098e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.040838e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.074373e+07 ) sec^-1 MeanMatrixElemValue = ( 1.008472e+02 +- 5.002447e+01 ) GeV^-2 -TOTAL : 0.453093 sec +TOTAL : 0.456865 sec INFO: No Floating Point Exceptions have been reported - 1,937,831,306 cycles # 2.897 GHz - 2,760,390,705 instructions # 1.42 insn per cycle - 0.725917028 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,922,600,682 cycles # 2.857 GHz + 2,735,771,538 instructions # 1.42 insn per cycle + 0.729676644 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 226 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.753006e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.403951e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.444556e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.681790e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.366127e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.406124e+07 ) sec^-1 MeanMatrixElemValue = ( 6.630097e+02 +- 4.770717e+02 ) GeV^-2 -TOTAL : 0.503839 sec +TOTAL : 0.509422 sec INFO: No Floating Point Exceptions have been reported - 2,122,411,110 cycles # 2.908 GHz - 3,090,140,496 instructions # 1.46 insn per cycle - 0.788810373 seconds time elapsed + 2,117,565,229 cycles # 2.869 GHz + 3,056,275,302 instructions # 1.44 insn per cycle + 0.796290434 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.412607e+00 Avg ME (F77/GPU) = 1.4132214305330990 Relative difference = 0.0004349621183379836 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.532382e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.545218e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.545218e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.491972e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.504565e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.504565e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 6.488008 sec +TOTAL : 6.593721 sec INFO: No Floating Point Exceptions have been reported - 19,400,700,603 cycles # 2.989 GHz - 59,351,001,772 instructions # 3.06 insn per cycle - 6.491955397 seconds time elapsed + 19,401,378,848 cycles # 2.941 GHz + 59,351,233,195 instructions # 3.06 insn per cycle + 6.597810534 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1027) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129949096991936 Relative difference = 6.390737857384068e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.590618e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.739335e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.739335e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.427450e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.574205e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.574205e+04 ) sec^-1 MeanMatrixElemValue = ( 1.009236e+02 +- 5.002643e+01 ) GeV^-2 -TOTAL : 1.924170 sec +TOTAL : 1.961524 sec INFO: No Floating Point Exceptions have been reported - 5,757,417,868 cycles # 2.987 GHz - 16,849,627,882 instructions # 2.93 insn per cycle - 1.928257529 seconds time elapsed + 5,763,417,063 cycles # 2.934 GHz + 16,848,552,420 instructions # 2.92 insn per cycle + 1.965663621 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5611) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.412995e+00 Avg ME (F77/C++) = 1.4129954647353316 Relative difference = 3.2890090308261873e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.552185e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.598756e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.598756e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.513418e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.559668e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.559668e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 1.073080 sec +TOTAL : 1.100420 sec INFO: No Floating Point Exceptions have been reported - 3,016,650,359 cycles # 2.803 GHz - 6,848,903,593 instructions # 2.27 insn per cycle - 1.077145956 seconds time elapsed + 3,014,454,268 cycles # 2.733 GHz + 6,847,622,992 instructions # 2.27 insn per cycle + 1.104094178 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 5735) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.683535e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.739951e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.739951e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.641246e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.695747e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.695747e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008857e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 0.990408 sec +TOTAL : 1.015943 sec INFO: No Floating Point Exceptions have been reported - 2,793,689,730 cycles # 2.811 GHz - 6,437,259,695 instructions # 2.30 insn per cycle - 0.994438549 seconds time elapsed + 2,793,517,683 cycles # 2.742 GHz + 6,436,907,448 instructions # 2.30 insn per cycle + 1.019630864 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 5509) (512y: 22) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413313e+00 Avg ME (F77/C++) = 1.4133132969790267 Relative difference = 2.1012969292986113e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.337472e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.374658e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.374658e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.322600e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.358678e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.358678e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008856e+02 +- 5.002468e+01 ) GeV^-2 -TOTAL : 1.245257 sec +TOTAL : 1.258576 sec INFO: No Floating Point Exceptions have been reported - 2,255,500,318 cycles # 1.807 GHz - 3,755,716,500 instructions # 1.67 insn per cycle - 1.249336626 seconds time elapsed + 2,248,626,373 cycles # 1.783 GHz + 3,754,168,834 instructions # 1.67 insn per cycle + 1.262333902 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2466) (512y: 29) (512z: 4084) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413316e+00 Avg ME (F77/C++) = 1.4133164033579249 Relative difference = 2.85398258307829e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd0.txt index f3f296c32..2641b6a6f 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:17:55 +DATE: 2024-09-15_11:14:59 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.829779e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.992225e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.088067e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.553984e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.813684e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.925982e+06 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 0.474231 sec +TOTAL : 0.473727 sec INFO: No Floating Point Exceptions have been reported - 1,991,666,593 cycles # 2.889 GHz - 2,862,009,939 instructions # 1.44 insn per cycle - 0.748188484 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,964,125,217 cycles # 2.842 GHz + 2,850,802,933 instructions # 1.45 insn per cycle + 0.747533169 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.052360e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.225527e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.235296e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.039046e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.224514e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.235497e+07 ) sec^-1 MeanMatrixElemValue = ( 6.734461e+02 +- 4.775415e+02 ) GeV^-2 -TOTAL : 0.605817 sec +TOTAL : 0.623745 sec INFO: No Floating Point Exceptions have been reported - 2,459,433,870 cycles # 2.917 GHz - 3,767,298,634 instructions # 1.53 insn per cycle - 0.901915026 seconds time elapsed + 2,491,113,981 cycles # 2.884 GHz + 3,741,355,868 instructions # 1.50 insn per cycle + 0.924633822 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.413122e+00 Avg ME (F77/GPU) = 1.4131213755569487 Relative difference = 4.418889885423659e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.430484e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.442316e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.442316e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.390069e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.401784e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.401784e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 6.761655 sec +TOTAL : 6.876043 sec INFO: No Floating Point Exceptions have been reported - 20,208,420,881 cycles # 2.987 GHz - 60,948,278,883 instructions # 3.02 insn per cycle - 6.765683895 seconds time elapsed + 20,176,006,103 cycles # 2.934 GHz + 60,944,588,650 instructions # 3.02 insn per cycle + 6.880217907 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1220) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213859069593 Relative difference = 4.345647726386255e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.712730e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.755397e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.755397e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.624106e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.667122e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.667122e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 3.496170 sec +TOTAL : 3.563355 sec INFO: No Floating Point Exceptions have been reported - 10,468,850,784 cycles # 2.992 GHz - 30,820,867,995 instructions # 2.94 insn per cycle - 3.500304414 seconds time elapsed + 10,467,283,500 cycles # 2.935 GHz + 30,820,693,493 instructions # 2.94 insn per cycle + 3.567171047 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5351) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213792564823 Relative difference = 4.392710025734405e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.398049e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.568353e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.568353e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.172379e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.336577e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.336577e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.763076 sec +TOTAL : 1.806966 sec INFO: No Floating Point Exceptions have been reported - 4,951,526,153 cycles # 2.803 GHz - 11,358,371,552 instructions # 2.29 insn per cycle - 1.767298886 seconds time elapsed + 4,954,879,411 cycles # 2.737 GHz + 11,359,422,816 instructions # 2.29 insn per cycle + 1.810872816 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4776) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213600217192 Relative difference = 4.5288254008796884e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.064444e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.086290e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.086290e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.036379e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.057513e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.057513e+05 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.558863 sec +TOTAL : 1.601666 sec INFO: No Floating Point Exceptions have been reported - 4,376,598,291 cycles # 2.801 GHz - 10,608,469,504 instructions # 2.42 insn per cycle - 1.562988882 seconds time elapsed + 4,380,983,099 cycles # 2.729 GHz + 10,610,165,712 instructions # 2.42 insn per cycle + 1.605990710 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4503) (512y: 83) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213600217192 Relative difference = 4.5288254008796884e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.134020e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.230854e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.230854e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.900446e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.995461e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.995461e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 2.318741 sec +TOTAL : 2.397174 sec INFO: No Floating Point Exceptions have been reported - 4,242,203,859 cycles # 1.827 GHz - 6,164,589,981 instructions # 1.45 insn per cycle - 2.323012442 seconds time elapsed + 4,245,323,919 cycles # 1.769 GHz + 6,166,210,089 instructions # 1.45 insn per cycle + 2.401100901 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2140) (512y: 117) (512z: 3653) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213786174055 Relative difference = 4.3972324717191576e-07 diff --git a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd1.txt index e346aeab2..0766319c3 100644 --- a/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg' -DATE: 2024-09-01_23:18:20 +DATE: 2024-09-15_11:15:25 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.798237e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.966504e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.065410e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.556212e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.906743e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.026143e+06 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 0.466648 sec +TOTAL : 0.472306 sec INFO: No Floating Point Exceptions have been reported - 2,016,435,863 cycles # 2.923 GHz - 2,910,161,803 instructions # 1.44 insn per cycle - 0.746914415 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,982,520,983 cycles # 2.874 GHz + 2,863,074,866 instructions # 1.44 insn per cycle + 0.745845869 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.060855e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.237227e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.247098e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.042838e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.231665e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.242155e+07 ) sec^-1 MeanMatrixElemValue = ( 6.734461e+02 +- 4.775415e+02 ) GeV^-2 -TOTAL : 0.600780 sec +TOTAL : 0.611235 sec INFO: No Floating Point Exceptions have been reported - 2,462,295,609 cycles # 2.931 GHz - 3,758,168,227 instructions # 1.53 insn per cycle - 0.898777357 seconds time elapsed + 2,455,829,243 cycles # 2.879 GHz + 3,741,729,771 instructions # 1.52 insn per cycle + 0.912428146 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.413122e+00 Avg ME (F77/GPU) = 1.4131213755569487 Relative difference = 4.418889885423659e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 2.423886e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.435676e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.435676e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.386940e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.398394e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.398394e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 6.780253 sec +TOTAL : 6.884140 sec INFO: No Floating Point Exceptions have been reported - 20,292,808,666 cycles # 2.992 GHz - 61,172,531,376 instructions # 3.01 insn per cycle - 6.784583027 seconds time elapsed + 20,272,568,697 cycles # 2.944 GHz + 61,168,730,148 instructions # 3.02 insn per cycle + 6.888274413 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1272) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213859069593 Relative difference = 4.345647726386255e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.781460e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.827050e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.827050e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.669440e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.713215e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.713215e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 3.445935 sec +TOTAL : 3.529000 sec INFO: No Floating Point Exceptions have been reported - 10,330,923,503 cycles # 2.995 GHz - 30,532,479,349 instructions # 2.96 insn per cycle - 3.450093687 seconds time elapsed + 10,335,535,502 cycles # 2.926 GHz + 30,533,410,675 instructions # 2.95 insn per cycle + 3.532867905 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 5155) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213792564823 Relative difference = 4.392710025734405e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.989697e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.145947e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.145947e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.803371e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.957146e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.957146e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.842100 sec +TOTAL : 1.880842 sec INFO: No Floating Point Exceptions have been reported - 5,140,656,602 cycles # 2.786 GHz - 11,872,353,123 instructions # 2.31 insn per cycle - 1.846234141 seconds time elapsed + 5,141,108,977 cycles # 2.729 GHz + 11,871,626,607 instructions # 2.31 insn per cycle + 1.885060685 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4887) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213600217192 Relative difference = 4.5288254008796884e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.988303e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.018035e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.018035e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.734351e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.920231e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.920231e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 1.659869 sec +TOTAL : 1.703697 sec INFO: No Floating Point Exceptions have been reported - 4,675,363,554 cycles # 2.811 GHz - 11,165,824,588 instructions # 2.39 insn per cycle - 1.664003607 seconds time elapsed + 4,677,605,202 cycles # 2.740 GHz + 11,166,557,237 instructions # 2.39 insn per cycle + 1.707597039 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4508) (512y: 238) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213600217192 Relative difference = 4.5288254008796884e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.142390e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.238965e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.238965e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.863155e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.956338e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.956338e+04 ) sec^-1 MeanMatrixElemValue = ( 1.008920e+02 +- 5.001681e+01 ) GeV^-2 -TOTAL : 2.315448 sec +TOTAL : 2.409053 sec INFO: No Floating Point Exceptions have been reported - 4,256,816,398 cycles # 1.836 GHz - 6,405,066,584 instructions # 1.50 insn per cycle - 2.319602248 seconds time elapsed + 4,255,960,621 cycles # 1.764 GHz + 6,404,237,522 instructions # 1.50 insn per cycle + 2.413297760 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2036) (512y: 163) (512z: 3731) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 16 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 16 channels { 1 : 64, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttg.mad/SubProcesses/P1_gg_ttxg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.413122e+00 Avg ME (F77/C++) = 1.4131213786174055 Relative difference = 4.3972324717191576e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0.txt index b16495d43..5f3726dce 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:18:46 +DATE: 2024-09-15_11:15:51 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.315060e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.337634e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.339238e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.308012e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.334511e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.336215e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.529607 sec +TOTAL : 0.533591 sec INFO: No Floating Point Exceptions have been reported - 2,229,815,269 cycles # 2.915 GHz - 3,529,273,827 instructions # 1.58 insn per cycle - 0.824163869 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 + 2,205,805,938 cycles # 2.869 GHz + 3,444,884,387 instructions # 1.56 insn per cycle + 0.825307966 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.140673e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.168228e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.169384e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.131073e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.161174e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.162405e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.031789 sec +TOTAL : 3.048991 sec INFO: No Floating Point Exceptions have been reported - 9,850,142,485 cycles # 2.985 GHz - 22,204,433,056 instructions # 2.25 insn per cycle - 3.356282362 seconds time elapsed + 9,688,028,273 cycles # 2.924 GHz + 22,036,541,373 instructions # 2.27 insn per cycle + 3.369850770 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.910726e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.911643e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.911643e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.879946e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.880868e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.880868e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.589540 sec +TOTAL : 8.730075 sec INFO: No Floating Point Exceptions have been reported - 25,627,728,244 cycles # 2.983 GHz - 78,955,696,602 instructions # 3.08 insn per cycle - 8.593772191 seconds time elapsed + 25,643,153,835 cycles # 2.937 GHz + 78,954,437,611 instructions # 3.08 insn per cycle + 8.734432118 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4842) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.589854e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.593135e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.593135e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.520374e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.523613e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.523613e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.574578 sec +TOTAL : 4.665332 sec INFO: No Floating Point Exceptions have been reported - 13,060,893,586 cycles # 2.853 GHz - 39,558,722,366 instructions # 3.03 insn per cycle - 4.578801220 seconds time elapsed + 13,099,128,105 cycles # 2.806 GHz + 39,559,591,481 instructions # 3.02 insn per cycle + 4.669271517 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13192) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.198901e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.216222e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.216222e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.059011e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.075081e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.075081e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.006726 sec +TOTAL : 2.042413 sec INFO: No Floating Point Exceptions have been reported - 5,614,026,038 cycles # 2.793 GHz - 13,824,406,079 instructions # 2.46 insn per cycle - 2.010944818 seconds time elapsed + 5,610,747,752 cycles # 2.743 GHz + 13,824,504,616 instructions # 2.46 insn per cycle + 2.046398223 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11520) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.359309e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.380862e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.380862e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.162703e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.184308e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.184308e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.758680 sec +TOTAL : 1.796726 sec INFO: No Floating Point Exceptions have been reported - 4,919,997,756 cycles # 2.792 GHz - 12,505,088,358 instructions # 2.54 insn per cycle - 1.762772156 seconds time elapsed + 4,922,237,700 cycles # 2.735 GHz + 12,506,994,545 instructions # 2.54 insn per cycle + 1.800589813 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10439) (512y: 88) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.179262e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.192439e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.192439e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.982168e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.994583e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.994583e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.290855 sec +TOTAL : 2.355452 sec INFO: No Floating Point Exceptions have been reported - 4,141,477,668 cycles # 1.805 GHz - 6,391,349,441 instructions # 1.54 insn per cycle - 2.295092021 seconds time elapsed + 4,140,123,386 cycles # 1.756 GHz + 6,390,153,387 instructions # 1.54 insn per cycle + 2.359734916 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1975) (512y: 102) (512z: 9386) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_bridge.txt index 0e41cfa3c..1d93db579 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:44:42 +DATE: 2024-09-15_11:48:14 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.989533e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.281981e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.281981e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.969430e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.268357e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.268357e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.522033 sec +TOTAL : 0.523555 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,202,251,491 cycles # 2.927 GHz - 3,503,930,284 instructions # 1.59 insn per cycle - 0.813886529 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 2,166,841,175 cycles # 2.867 GHz + 3,453,451,458 instructions # 1.59 insn per cycle + 0.814918597 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.635230e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.122249e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.122249e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.613032e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.091578e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.091578e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.305275 sec +TOTAL : 3.317499 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 10,626,401,811 cycles # 2.970 GHz - 22,283,600,258 instructions # 2.10 insn per cycle - 3.635886705 seconds time elapsed + 10,422,723,136 cycles # 2.898 GHz + 15,879,167,379 instructions # 1.52 insn per cycle + 3.658545225 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.911101e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.912003e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.912003e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.878765e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.879684e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.879684e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.591953 sec +TOTAL : 8.741583 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 25,658,745,754 cycles # 2.985 GHz - 78,961,778,827 instructions # 3.08 insn per cycle - 8.596346628 seconds time elapsed + 25,666,397,830 cycles # 2.935 GHz + 78,965,262,045 instructions # 3.08 insn per cycle + 8.745862119 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4842) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.579531e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.582836e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.582836e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.560977e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.564368e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.564368e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.591842 sec +TOTAL : 4.617447 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 13,090,469,361 cycles # 2.849 GHz - 39,572,230,574 instructions # 3.02 insn per cycle - 4.596399381 seconds time elapsed + 13,088,026,122 cycles # 2.833 GHz + 39,572,731,788 instructions # 3.02 insn per cycle + 4.621932955 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13192) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.191077e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.208104e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.208104e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.016507e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.032941e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.032941e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.012743 sec +TOTAL : 2.058059 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 5,624,310,938 cycles # 2.789 GHz - 13,834,627,183 instructions # 2.46 insn per cycle - 2.017253922 seconds time elapsed + 5,631,279,447 cycles # 2.732 GHz + 13,836,775,240 instructions # 2.46 insn per cycle + 2.062638485 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11520) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.291143e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.314088e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.314088e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.172752e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.195878e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.195878e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.775535 sec +TOTAL : 1.800276 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,937,092,344 cycles # 2.775 GHz - 12,517,222,540 instructions # 2.54 insn per cycle - 1.779883373 seconds time elapsed + 4,940,734,767 cycles # 2.740 GHz + 12,518,660,568 instructions # 2.53 insn per cycle + 1.804734715 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10439) (512y: 88) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.075955e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.088365e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.088365e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.912888e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.925297e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.925297e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.328033 sec +TOTAL : 2.384873 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,154,862,662 cycles # 1.782 GHz - 6,403,687,293 instructions # 1.54 insn per cycle - 2.332579074 seconds time elapsed + 4,161,817,801 cycles # 1.743 GHz + 6,405,054,448 instructions # 1.54 insn per cycle + 2.389410885 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1975) (512y: 102) (512z: 9386) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_common.txt index c2df789ac..fc2e4b7aa 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:55:28 +DATE: 2024-09-15_11:59:16 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.330394e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.354681e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.356479e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.322702e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.346002e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.347615e+05 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 0.516014 sec +TOTAL : 0.517480 sec INFO: No Floating Point Exceptions have been reported - 2,169,057,551 cycles # 2.913 GHz - 3,493,264,432 instructions # 1.61 insn per cycle - 0.806582698 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --common + 2,154,192,085 cycles # 2.875 GHz + 3,384,532,263 instructions # 1.57 insn per cycle + 0.808566781 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.127429e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.159380e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.160647e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.137866e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.167359e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.168584e+05 ) sec^-1 MeanMatrixElemValue = ( 1.252232e+02 +- 1.234346e+02 ) GeV^-4 -TOTAL : 3.140428 sec +TOTAL : 3.158061 sec INFO: No Floating Point Exceptions have been reported - 10,120,833,598 cycles # 2.979 GHz - 21,427,031,047 instructions # 2.12 insn per cycle - 3.454066352 seconds time elapsed + 9,917,250,541 cycles # 2.905 GHz + 22,199,780,027 instructions # 2.24 insn per cycle + 3.469925481 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.903992e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.904921e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.904921e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.876744e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.877706e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.877706e+03 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 8.621406 sec +TOTAL : 8.747062 sec INFO: No Floating Point Exceptions have been reported - 25,663,807,868 cycles # 2.976 GHz - 78,956,902,054 instructions # 3.08 insn per cycle - 8.627193724 seconds time elapsed + 25,648,612,426 cycles # 2.931 GHz + 78,952,780,288 instructions # 3.08 insn per cycle + 8.750949596 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4842) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.624340e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.627627e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.627627e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.516490e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.519795e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.519795e+03 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 4.532651 sec +TOTAL : 4.672214 sec INFO: No Floating Point Exceptions have been reported - 13,057,282,573 cycles # 2.879 GHz - 39,558,198,359 instructions # 3.03 insn per cycle - 4.536719035 seconds time elapsed + 13,064,181,413 cycles # 2.795 GHz + 39,557,975,845 instructions # 3.03 insn per cycle + 4.676162125 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13192) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.204978e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.221960e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.221960e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.035027e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.051957e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.051957e+03 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 2.006568 sec +TOTAL : 2.050050 sec INFO: No Floating Point Exceptions have been reported - 5,618,687,412 cycles # 2.795 GHz - 13,822,855,763 instructions # 2.46 insn per cycle - 2.010749099 seconds time elapsed + 5,620,854,320 cycles # 2.738 GHz + 13,824,518,317 instructions # 2.46 insn per cycle + 2.054209584 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11520) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.344898e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.366603e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.366603e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.147098e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.168017e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.168017e+03 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 1.762820 sec +TOTAL : 1.801905 sec INFO: No Floating Point Exceptions have been reported - 4,933,693,544 cycles # 2.794 GHz - 12,504,027,488 instructions # 2.53 insn per cycle - 1.766918683 seconds time elapsed + 4,929,552,945 cycles # 2.731 GHz + 12,503,971,607 instructions # 2.54 insn per cycle + 1.805808510 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10439) (512y: 88) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.216455e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.229143e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.229143e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.940588e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.953237e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.953237e+03 ) sec^-1 MeanMatrixElemValue = ( 4.197467e-01 +- 3.250467e-01 ) GeV^-4 -TOTAL : 2.280566 sec +TOTAL : 2.372033 sec INFO: No Floating Point Exceptions have been reported - 4,150,319,540 cycles # 1.817 GHz - 6,389,476,563 instructions # 1.54 insn per cycle - 2.284688942 seconds time elapsed + 4,149,036,914 cycles # 1.747 GHz + 6,390,952,192 instructions # 1.54 insn per cycle + 2.375889237 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1975) (512y: 102) (512z: 9386) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_curhst.txt index d0233b939..989861023 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:52:39 +DATE: 2024-09-15_11:56:23 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.318416e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.342529e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.344516e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.313175e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.336829e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.338592e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.514493 sec +TOTAL : 0.516520 sec INFO: No Floating Point Exceptions have been reported - 2,165,328,295 cycles # 2.912 GHz - 3,440,104,971 instructions # 1.59 insn per cycle - 0.805805306 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst + 2,145,509,423 cycles # 2.867 GHz + 3,354,996,461 instructions # 1.56 insn per cycle + 0.808722776 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.134192e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.166205e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.167551e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.143109e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.171681e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.172874e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.076661 sec +TOTAL : 3.078670 sec INFO: No Floating Point Exceptions have been reported - 9,913,932,835 cycles # 2.974 GHz - 22,782,867,940 instructions # 2.30 insn per cycle - 3.391164141 seconds time elapsed + 9,691,265,584 cycles # 2.906 GHz + 21,333,506,403 instructions # 2.20 insn per cycle + 3.390410721 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.920273e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.921234e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.921234e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.881675e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.882585e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.882585e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.546594 sec +TOTAL : 8.722848 sec INFO: No Floating Point Exceptions have been reported - 25,646,311,324 cycles # 3.000 GHz - 78,960,017,472 instructions # 3.08 insn per cycle - 8.550676592 seconds time elapsed + 25,651,425,779 cycles # 2.940 GHz + 78,952,412,711 instructions # 3.08 insn per cycle + 8.726726338 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4842) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.594154e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.597374e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.597374e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.517566e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.520849e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.520849e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.568989 sec +TOTAL : 4.669337 sec INFO: No Floating Point Exceptions have been reported - 13,102,878,898 cycles # 2.866 GHz - 39,561,274,098 instructions # 3.02 insn per cycle - 4.573103208 seconds time elapsed + 13,090,805,200 cycles # 2.802 GHz + 39,558,366,602 instructions # 3.02 insn per cycle + 4.673224740 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13192) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.221553e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.238357e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.238357e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.039895e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.055822e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.055822e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.000959 sec +TOTAL : 2.046582 sec INFO: No Floating Point Exceptions have been reported - 5,606,842,172 cycles # 2.797 GHz - 13,823,630,038 instructions # 2.47 insn per cycle - 2.005081475 seconds time elapsed + 5,609,737,694 cycles # 2.737 GHz + 13,824,245,582 instructions # 2.46 insn per cycle + 2.050512234 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11520) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.323867e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.345458e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.345458e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.131967e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.152226e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.152226e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.765274 sec +TOTAL : 1.803136 sec INFO: No Floating Point Exceptions have been reported - 4,923,007,337 cycles # 2.783 GHz - 12,505,051,193 instructions # 2.54 insn per cycle - 1.769470001 seconds time elapsed + 4,925,220,417 cycles # 2.727 GHz + 12,506,075,504 instructions # 2.54 insn per cycle + 1.807026447 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10439) (512y: 88) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.173442e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.186199e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.186199e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.955213e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.967580e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.967580e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.292842 sec +TOTAL : 2.365271 sec INFO: No Floating Point Exceptions have been reported - 4,144,135,456 cycles # 1.805 GHz - 6,391,162,760 instructions # 1.54 insn per cycle - 2.297102234 seconds time elapsed + 4,141,642,997 cycles # 1.749 GHz + 6,391,703,659 instructions # 1.54 insn per cycle + 2.369209251 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1975) (512y: 102) (512z: 9386) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_rmbhst.txt index 635f9015c..794fb1a80 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,76 +11,76 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:49:56 +DATE: 2024-09-15_11:53:35 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.081101e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.356424e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.358297e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.043181e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.332865e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.334802e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.517092 sec +TOTAL : 0.523228 sec INFO: No Floating Point Exceptions have been reported - 2,169,776,798 cycles # 2.903 GHz - 3,470,342,653 instructions # 1.60 insn per cycle - 0.807877251 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst + 2,169,607,107 cycles # 2.877 GHz + 3,459,237,306 instructions # 1.59 insn per cycle + 0.815202021 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.731419e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.163821e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.165190e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.724697e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.162122e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.163349e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.207952 sec +TOTAL : 3.220306 sec INFO: No Floating Point Exceptions have been reported - 10,211,555,385 cycles # 2.948 GHz - 21,576,803,795 instructions # 2.11 insn per cycle - 3.520497556 seconds time elapsed + 10,133,189,238 cycles # 2.914 GHz + 23,148,993,968 instructions # 2.28 insn per cycle + 3.534065636 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -88,33 +88,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.919767e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.920710e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.920710e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.879192e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.880098e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.880098e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.548661 sec +TOTAL : 8.734016 sec INFO: No Floating Point Exceptions have been reported - 25,650,941,063 cycles # 3.000 GHz - 78,955,343,064 instructions # 3.08 insn per cycle - 8.552742436 seconds time elapsed + 25,661,507,280 cycles # 2.937 GHz + 78,953,590,713 instructions # 3.08 insn per cycle + 8.737772518 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4842) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -122,31 +122,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.513813e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.516942e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.516942e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.527947e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.531121e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.531121e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.673624 sec +TOTAL : 4.656259 sec INFO: No Floating Point Exceptions have been reported - 13,066,932,507 cycles # 2.794 GHz - 39,559,326,469 instructions # 3.03 insn per cycle - 4.677800727 seconds time elapsed + 13,056,695,540 cycles # 2.803 GHz + 39,560,471,761 instructions # 3.03 insn per cycle + 4.660116201 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13192) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -154,31 +154,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.202148e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.218438e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.218438e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.991321e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.007389e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.007389e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.005511 sec +TOTAL : 2.059547 sec INFO: No Floating Point Exceptions have been reported - 5,606,683,157 cycles # 2.791 GHz - 13,823,530,699 instructions # 2.47 insn per cycle - 2.009685853 seconds time elapsed + 5,612,692,411 cycles # 2.721 GHz + 13,825,461,651 instructions # 2.46 insn per cycle + 2.063599543 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11520) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -186,31 +186,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.377013e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.399305e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.399305e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.168393e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.189788e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.189788e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.755095 sec +TOTAL : 1.795888 sec INFO: No Floating Point Exceptions have been reported - 4,921,086,197 cycles # 2.798 GHz - 12,505,079,449 instructions # 2.54 insn per cycle - 1.759276338 seconds time elapsed + 4,923,088,043 cycles # 2.737 GHz + 12,506,721,234 instructions # 2.54 insn per cycle + 1.799844991 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10439) (512y: 88) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -218,31 +218,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.166192e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.180300e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.180300e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.949785e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.962226e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.962226e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.295174 sec +TOTAL : 2.367179 sec INFO: No Floating Point Exceptions have been reported - 4,143,137,312 cycles # 1.802 GHz - 6,391,191,490 instructions # 1.54 insn per cycle - 2.299503002 seconds time elapsed + 4,144,948,568 cycles # 1.750 GHz + 6,391,796,529 instructions # 1.54 insn per cycle + 2.371216811 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1975) (512y: 102) (512z: 9386) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -250,8 +250,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd1.txt index 8702657ea..80da0089a 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:19:20 +DATE: 2024-09-15_11:16:25 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.329626e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.352172e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.354025e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.297695e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.326014e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.328135e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.528976 sec +TOTAL : 0.536243 sec INFO: No Floating Point Exceptions have been reported - 2,235,005,557 cycles # 2.928 GHz - 3,523,767,617 instructions # 1.58 insn per cycle - 0.822200243 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 + 2,198,395,650 cycles # 2.855 GHz + 3,395,768,128 instructions # 1.54 insn per cycle + 0.828484590 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.150039e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.177704e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.178867e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.139738e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.170223e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.171507e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.028533 sec +TOTAL : 3.043962 sec INFO: No Floating Point Exceptions have been reported - 9,771,225,354 cycles # 2.968 GHz - 20,608,619,362 instructions # 2.11 insn per cycle - 3.348285124 seconds time elapsed + 9,646,114,898 cycles # 2.920 GHz + 22,170,499,370 instructions # 2.30 insn per cycle + 3.361578134 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158133E-004 Relative difference = 2.837296512218831e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.914314e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.915252e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.915252e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.884927e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.885834e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.885834e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.573222 sec +TOTAL : 8.707889 sec INFO: No Floating Point Exceptions have been reported - 25,658,733,071 cycles # 2.992 GHz - 78,700,903,284 instructions # 3.07 insn per cycle - 8.577401591 seconds time elapsed + 25,619,332,595 cycles # 2.941 GHz + 78,702,929,908 instructions # 3.07 insn per cycle + 8.712420077 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4191) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141133E-004 Relative difference = 2.8372990776517314e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.626644e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.629945e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.629945e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.574307e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.577560e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.577560e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.528164 sec +TOTAL : 4.595188 sec INFO: No Floating Point Exceptions have been reported - 13,032,300,901 cycles # 2.876 GHz - 39,448,920,452 instructions # 3.03 insn per cycle - 4.532355358 seconds time elapsed + 13,048,399,086 cycles # 2.838 GHz + 39,450,691,251 instructions # 3.02 insn per cycle + 4.599210719 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:12966) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141122E-004 Relative difference = 2.837299079287849e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.099683e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.115929e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.115929e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.930739e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.946422e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.946422e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.030785 sec +TOTAL : 2.074898 sec INFO: No Floating Point Exceptions have been reported - 5,686,751,600 cycles # 2.796 GHz - 13,911,142,235 instructions # 2.45 insn per cycle - 2.034951048 seconds time elapsed + 5,675,338,380 cycles # 2.732 GHz + 13,910,840,784 instructions # 2.45 insn per cycle + 2.079006346 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11582) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.268666e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.290003e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.290003e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.062486e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.083766e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.083766e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.775645 sec +TOTAL : 1.816561 sec INFO: No Floating Point Exceptions have been reported - 4,993,199,393 cycles # 2.807 GHz - 12,602,433,108 instructions # 2.52 insn per cycle - 1.779957429 seconds time elapsed + 4,996,440,015 cycles # 2.746 GHz + 12,603,390,155 instructions # 2.52 insn per cycle + 1.820566072 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10423) (512y: 240) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.206059e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.219386e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.219386e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.965367e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.977715e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.977715e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.282127 sec +TOTAL : 2.361480 sec INFO: No Floating Point Exceptions have been reported - 4,159,427,245 cycles # 1.820 GHz - 6,499,223,807 instructions # 1.56 insn per cycle - 2.286309091 seconds time elapsed + 4,159,091,159 cycles # 1.759 GHz + 6,499,576,244 instructions # 1.56 insn per cycle + 2.365402468 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1751) (512y: 194) (512z: 9382) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198157320E-004 Relative difference = 2.837296634927675e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd0.txt index 96ffb76cf..a149b91e1 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:35:14 +DATE: 2024-09-15_11:36:57 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.097238e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.116880e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.118273e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.106076e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.131267e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.133080e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.537823 sec +TOTAL : 0.544695 sec INFO: No Floating Point Exceptions have been reported - 2,250,719,878 cycles # 2.921 GHz - 3,578,968,848 instructions # 1.59 insn per cycle - 0.827505559 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 64 256 1 + 2,219,428,600 cycles # 2.858 GHz + 3,493,527,234 instructions # 1.57 insn per cycle + 0.834499500 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.751486e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.775770e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.776803e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.753348e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.778591e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.779655e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.302670 sec +TOTAL : 3.312449 sec INFO: No Floating Point Exceptions have been reported - 10,538,630,307 cycles # 2.961 GHz - 24,318,411,648 instructions # 2.31 insn per cycle - 3.614850320 seconds time elapsed + 10,421,899,087 cycles # 2.913 GHz + 24,058,421,553 instructions # 2.31 insn per cycle + 3.636091022 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158122E-004 Relative difference = 2.837296513854949e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 4.356633e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.357117e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.357117e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.268976e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.269450e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.269450e+02 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 37.650558 sec +TOTAL : 38.423779 sec INFO: No Floating Point Exceptions have been reported - 112,738,803,262 cycles # 2.994 GHz - 144,792,925,936 instructions # 1.28 insn per cycle - 37.654827076 seconds time elapsed + 112,730,268,623 cycles # 2.934 GHz + 144,772,135,406 instructions # 1.28 insn per cycle + 38.427951659 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:21273) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198140461E-004 Relative difference = 2.8372991790910424e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.143637e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.146289e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.146289e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.077363e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.079742e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.079742e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 5.223092 sec +TOTAL : 5.335511 sec INFO: No Floating Point Exceptions have been reported - 14,749,878,339 cycles # 2.822 GHz - 37,648,636,162 instructions # 2.55 insn per cycle - 5.227369590 seconds time elapsed + 14,752,370,812 cycles # 2.763 GHz + 37,645,694,563 instructions # 2.55 insn per cycle + 5.339828429 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:68253) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141209E-004 Relative difference = 2.8372990661989057e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.539545e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.554230e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.554230e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.332306e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.345602e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.345602e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.181602 sec +TOTAL : 2.243210 sec INFO: No Floating Point Exceptions have been reported - 6,123,137,248 cycles # 2.802 GHz - 13,060,513,042 instructions # 2.13 insn per cycle - 2.185812086 seconds time elapsed + 6,130,370,628 cycles # 2.729 GHz + 13,060,931,234 instructions # 2.13 insn per cycle + 2.247428561 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:46973) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.142318e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.163428e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.163428e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.812729e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.832105e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.832105e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.800190 sec +TOTAL : 1.867280 sec INFO: No Floating Point Exceptions have been reported - 5,062,465,914 cycles # 2.807 GHz - 11,454,182,692 instructions # 2.26 insn per cycle - 1.804398301 seconds time elapsed + 5,063,580,201 cycles # 2.707 GHz + 11,453,397,200 instructions # 2.26 insn per cycle + 1.871531437 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:40498) (512y: 285) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.490777e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.504795e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.504795e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.266726e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.280024e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.280024e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.195736 sec +TOTAL : 2.263638 sec INFO: No Floating Point Exceptions have been reported - 3,951,905,441 cycles # 1.797 GHz - 5,928,043,150 instructions # 1.50 insn per cycle - 2.199938848 seconds time elapsed + 3,957,788,966 cycles # 1.746 GHz + 5,926,468,977 instructions # 1.50 insn per cycle + 2.267826067 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2444) (512y: 337) (512z:39349) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd1.txt index ef5b0520d..c0add05aa 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_d_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:36:22 +DATE: 2024-09-15_11:38:07 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.106464e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.130019e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.131660e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.096121e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.123086e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.125058e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.536986 sec +TOTAL : 0.541972 sec INFO: No Floating Point Exceptions have been reported - 2,245,613,083 cycles # 2.928 GHz - 3,531,927,717 instructions # 1.57 insn per cycle - 0.825355433 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 64 256 1 + 2,219,963,696 cycles # 2.870 GHz + 3,470,909,979 instructions # 1.56 insn per cycle + 0.830712751 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.743190e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.767517e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.768547e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.756387e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.782287e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.783295e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.299173 sec +TOTAL : 3.298693 sec INFO: No Floating Point Exceptions have been reported - 10,563,427,043 cycles # 2.972 GHz - 24,228,869,138 instructions # 2.29 insn per cycle - 3.612557038 seconds time elapsed + 10,399,316,447 cycles # 2.922 GHz + 23,584,057,660 instructions # 2.27 insn per cycle + 3.614068267 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_d_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266731198158122E-004 Relative difference = 2.837296513854949e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_d_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 4.301726e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.302192e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.302192e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.224460e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.224899e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.224899e+02 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 38.130581 sec +TOTAL : 38.827526 sec INFO: No Floating Point Exceptions have been reported - 113,774,788,028 cycles # 2.984 GHz - 144,279,987,880 instructions # 1.27 insn per cycle - 38.134610815 seconds time elapsed + 113,783,414,735 cycles # 2.930 GHz + 144,278,309,276 instructions # 1.27 insn per cycle + 38.831628591 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:21024) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198140450E-004 Relative difference = 2.83729918072716e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.058351e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.060826e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.060826e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.989108e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.991357e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.991357e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 5.368552 sec +TOTAL : 5.492626 sec INFO: No Floating Point Exceptions have been reported - 15,303,684,701 cycles # 2.849 GHz - 38,390,561,420 instructions # 2.51 insn per cycle - 5.372764017 seconds time elapsed + 15,275,599,565 cycles # 2.780 GHz + 38,389,599,156 instructions # 2.51 insn per cycle + 5.496788286 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:69643) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198141209E-004 Relative difference = 2.8372990661989057e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.700721e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.715343e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.715343e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.497881e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.512338e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.512338e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.135636 sec +TOTAL : 2.193501 sec INFO: No Floating Point Exceptions have been reported - 6,011,281,562 cycles # 2.810 GHz - 12,934,915,193 instructions # 2.15 insn per cycle - 2.139765113 seconds time elapsed + 6,019,122,923 cycles # 2.740 GHz + 12,933,620,431 instructions # 2.15 insn per cycle + 2.197765722 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:46099) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.081941e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.102133e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.102133e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.839318e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.859960e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.859960e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.811792 sec +TOTAL : 1.861821 sec INFO: No Floating Point Exceptions have been reported - 5,089,368,793 cycles # 2.804 GHz - 11,449,399,387 instructions # 2.25 insn per cycle - 1.815957052 seconds time elapsed + 5,093,783,286 cycles # 2.731 GHz + 11,449,481,812 instructions # 2.25 insn per cycle + 1.866150033 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:40142) (512y: 219) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.589010e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.603957e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.603957e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.279822e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.293417e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.293417e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.167801 sec +TOTAL : 2.259516 sec INFO: No Floating Point Exceptions have been reported - 3,945,734,127 cycles # 1.817 GHz - 5,888,838,565 instructions # 1.49 insn per cycle - 2.172122091 seconds time elapsed + 3,958,337,222 cycles # 1.750 GHz + 5,889,113,860 instructions # 1.49 insn per cycle + 2.263750575 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1959) (512y: 259) (512z:38927) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_d_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731198156789E-004 Relative difference = 2.837296715097453e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0.txt index a6de8a92c..f53bdfcb0 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:19:53 +DATE: 2024-09-15_11:16:59 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.525526e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.560984e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.564965e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.467249e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.509285e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.513718e+05 ) sec^-1 MeanMatrixElemValue = ( 4.059596e+00 +- 2.368053e+00 ) GeV^-4 -TOTAL : 0.492424 sec +TOTAL : 0.494218 sec INFO: No Floating Point Exceptions have been reported - 2,001,879,633 cycles # 2.819 GHz - 3,019,819,984 instructions # 1.51 insn per cycle - 0.769396542 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 + 2,034,103,432 cycles # 2.860 GHz + 3,045,186,386 instructions # 1.50 insn per cycle + 0.768364063 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.137089e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.191445e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.193924e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.128844e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.190571e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.193248e+05 ) sec^-1 MeanMatrixElemValue = ( 6.664703e+00 +- 5.072736e+00 ) GeV^-4 -TOTAL : 1.794834 sec +TOTAL : 1.796967 sec INFO: No Floating Point Exceptions have been reported - 5,999,042,027 cycles # 2.947 GHz - 12,933,175,351 instructions # 2.16 insn per cycle - 2.095708185 seconds time elapsed + 5,948,917,067 cycles # 2.924 GHz + 12,254,957,631 instructions # 2.06 insn per cycle + 2.089755272 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.962685e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.963647e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.963647e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.939424e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.940380e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.940380e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060121e+00 +- 2.367902e+00 ) GeV^-4 -TOTAL : 8.361298 sec +TOTAL : 8.461205 sec INFO: No Floating Point Exceptions have been reported - 24,937,506,812 cycles # 2.982 GHz - 79,113,828,402 instructions # 3.17 insn per cycle - 8.365325330 seconds time elapsed + 24,939,277,475 cycles # 2.947 GHz + 79,109,068,255 instructions # 3.17 insn per cycle + 8.465315543 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274863312764526E-004 Relative difference = 4.998523613136231e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.116873e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.129943e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.129943e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.989306e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.001573e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.001573e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060119e+00 +- 2.367901e+00 ) GeV^-4 -TOTAL : 2.309301 sec +TOTAL : 2.351266 sec INFO: No Floating Point Exceptions have been reported - 6,531,767,755 cycles # 2.824 GHz - 20,271,250,387 instructions # 3.10 insn per cycle - 2.313702533 seconds time elapsed + 6,525,064,847 cycles # 2.771 GHz + 20,269,487,959 instructions # 3.11 insn per cycle + 2.355049106 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13779) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861442972011E-004 Relative difference = 2.1772539563413118e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.630164e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.636943e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.636943e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.582613e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.589051e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.589051e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 1.011713 sec +TOTAL : 1.041194 sec INFO: No Floating Point Exceptions have been reported - 2,849,688,057 cycles # 2.807 GHz - 7,066,344,339 instructions # 2.48 insn per cycle - 1.015815872 seconds time elapsed + 2,848,829,047 cycles # 2.729 GHz + 7,065,493,216 instructions # 2.48 insn per cycle + 1.044894531 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12055) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.849480e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.858102e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.858102e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.794003e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.802231e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.802231e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 0.891670 sec +TOTAL : 0.919231 sec INFO: No Floating Point Exceptions have been reported - 2,522,839,359 cycles # 2.818 GHz - 6,403,669,992 instructions # 2.54 insn per cycle - 0.895820914 seconds time elapsed + 2,522,001,135 cycles # 2.735 GHz + 6,403,495,458 instructions # 2.54 insn per cycle + 0.923373159 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11021) (512y: 43) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.457100e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.462451e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.462451e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.403418e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.408437e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.408437e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060562e+00 +- 2.367612e+00 ) GeV^-4 -TOTAL : 1.130822 sec +TOTAL : 1.173408 sec INFO: No Floating Point Exceptions have been reported - 2,069,347,920 cycles # 1.824 GHz - 3,303,789,535 instructions # 1.60 insn per cycle - 1.135015326 seconds time elapsed + 2,065,585,282 cycles # 1.756 GHz + 3,303,212,083 instructions # 1.60 insn per cycle + 1.177101647 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2601) (512y: 46) (512z: 9605) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952779718007E-004 Relative difference = 4.194411063934945e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_bridge.txt index b61796eb5..99ccf0b7c 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:45:16 +DATE: 2024-09-15_11:48:48 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.950659e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.505059e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.505059e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.945945e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.468849e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.468849e+05 ) sec^-1 MeanMatrixElemValue = ( 4.048178e+00 +- 2.364571e+00 ) GeV^-4 -TOTAL : 0.476846 sec +TOTAL : 0.482042 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,018,132,291 cycles # 2.915 GHz - 3,077,441,374 instructions # 1.52 insn per cycle - 0.749610068 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 1,997,062,353 cycles # 2.864 GHz + 3,031,546,242 instructions # 1.52 insn per cycle + 0.755384112 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.950025e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.080536e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.080536e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.954589e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.017029e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.017029e+05 ) sec^-1 MeanMatrixElemValue = ( 6.641709e+00 +- 4.994248e+00 ) GeV^-4 -TOTAL : 1.969137 sec +TOTAL : 2.150287 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,563,176,344 cycles # 2.957 GHz - 14,010,044,711 instructions # 2.13 insn per cycle - 2.277055445 seconds time elapsed + 6,911,046,669 cycles # 2.894 GHz + 9,720,301,924 instructions # 1.41 insn per cycle + 2.447262326 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.975190e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.976183e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.976183e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.933142e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.934088e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.934088e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060121e+00 +- 2.367902e+00 ) GeV^-4 -TOTAL : 8.310516 sec +TOTAL : 8.491300 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 24,940,948,507 cycles # 3.000 GHz - 79,113,943,646 instructions # 3.17 insn per cycle - 8.314719259 seconds time elapsed + 24,914,436,852 cycles # 2.933 GHz + 79,112,976,787 instructions # 3.18 insn per cycle + 8.495346137 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274863312764526E-004 Relative difference = 4.998523613136231e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.173055e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.186375e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.186375e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.985457e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.998623e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.998623e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060119e+00 +- 2.367901e+00 ) GeV^-4 -TOTAL : 2.293926 sec +TOTAL : 2.355396 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,540,473,256 cycles # 2.847 GHz - 20,280,249,725 instructions # 3.10 insn per cycle - 2.298218918 seconds time elapsed + 6,536,388,186 cycles # 2.771 GHz + 20,278,657,318 instructions # 3.10 insn per cycle + 2.359340287 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13779) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861442972011E-004 Relative difference = 2.1772539563413118e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.621304e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.628040e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.628040e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.588469e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.595113e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.595113e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 1.019285 sec +TOTAL : 1.040170 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,858,228,957 cycles # 2.794 GHz - 7,075,917,816 instructions # 2.48 insn per cycle - 1.023527550 seconds time elapsed + 2,854,653,705 cycles # 2.736 GHz + 7,075,192,119 instructions # 2.48 insn per cycle + 1.044116961 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12055) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.847241e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.855664e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.855664e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.764583e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.772721e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.772721e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 0.895280 sec +TOTAL : 0.937436 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,529,427,682 cycles # 2.814 GHz - 6,413,812,862 instructions # 2.54 insn per cycle - 0.899477275 seconds time elapsed + 2,529,004,808 cycles # 2.688 GHz + 6,413,196,189 instructions # 2.54 insn per cycle + 0.941494819 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11021) (512y: 43) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.472092e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.477566e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.477566e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.393518e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.398724e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.398724e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060562e+00 +- 2.367612e+00 ) GeV^-4 -TOTAL : 1.122188 sec +TOTAL : 1.184860 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,077,583,112 cycles # 1.845 GHz - 3,314,052,942 instructions # 1.60 insn per cycle - 1.126483602 seconds time elapsed + 2,077,752,907 cycles # 1.749 GHz + 3,313,647,639 instructions # 1.59 insn per cycle + 1.188846310 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2601) (512y: 46) (512z: 9605) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952779718007E-004 Relative difference = 4.194411063934945e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_common.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_common.txt index 1b7d8e33c..19f64c3e7 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_common.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_common.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:56:01 +DATE: 2024-09-15_11:59:51 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.508785e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.546625e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.550440e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.517186e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.553165e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.556664e+05 ) sec^-1 MeanMatrixElemValue = ( 4.159396e-01 +- 3.238803e-01 ) GeV^-4 -TOTAL : 0.473604 sec +TOTAL : 0.477606 sec INFO: No Floating Point Exceptions have been reported - 2,017,340,152 cycles # 2.933 GHz - 3,080,271,867 instructions # 1.53 insn per cycle - 0.745522319 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --common + 1,989,569,741 cycles # 2.873 GHz + 3,005,042,417 instructions # 1.51 insn per cycle + 0.749585148 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --common ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:COMMON+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.132695e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.194961e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.197817e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.132207e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.190283e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.192869e+05 ) sec^-1 MeanMatrixElemValue = ( 1.094367e+02 +- 1.071509e+02 ) GeV^-4 -TOTAL : 1.870998 sec +TOTAL : 1.892599 sec INFO: No Floating Point Exceptions have been reported - 6,188,150,786 cycles # 2.945 GHz - 12,176,753,673 instructions # 1.97 insn per cycle - 2.156923874 seconds time elapsed + 6,180,255,032 cycles # 2.913 GHz + 13,158,154,431 instructions # 2.13 insn per cycle + 2.179693271 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.971622e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.972577e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.972577e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.919400e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.920348e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.920348e+03 ) sec^-1 MeanMatrixElemValue = ( 4.208459e-01 +- 3.253446e-01 ) GeV^-4 -TOTAL : 8.324572 sec +TOTAL : 8.550896 sec INFO: No Floating Point Exceptions have been reported - 24,943,820,538 cycles # 2.996 GHz - 79,110,662,739 instructions # 3.17 insn per cycle - 8.328497474 seconds time elapsed + 24,917,761,266 cycles # 2.921 GHz + 79,107,928,249 instructions # 3.17 insn per cycle + 8.554412617 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274863312764526E-004 Relative difference = 4.998523613136231e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.128415e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.141771e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.141771e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.947395e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.959971e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.959971e+03 ) sec^-1 MeanMatrixElemValue = ( 4.208457e-01 +- 3.253445e-01 ) GeV^-4 -TOTAL : 2.307045 sec +TOTAL : 2.367170 sec INFO: No Floating Point Exceptions have been reported - 6,543,184,083 cycles # 2.833 GHz - 20,272,761,591 instructions # 3.10 insn per cycle - 2.311035863 seconds time elapsed + 6,537,639,637 cycles # 2.759 GHz + 20,270,199,231 instructions # 3.10 insn per cycle + 2.370801699 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13779) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861442972011E-004 Relative difference = 2.1772539563413118e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.627514e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.634489e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.634489e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.589719e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.596352e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.596352e+04 ) sec^-1 MeanMatrixElemValue = ( 4.214978e-01 +- 3.255521e-01 ) GeV^-4 -TOTAL : 1.013506 sec +TOTAL : 1.038242 sec INFO: No Floating Point Exceptions have been reported - 2,853,225,522 cycles # 2.806 GHz - 7,063,897,484 instructions # 2.48 insn per cycle - 1.017452145 seconds time elapsed + 2,854,773,942 cycles # 2.742 GHz + 7,065,309,093 instructions # 2.47 insn per cycle + 1.041774606 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12055) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.742068e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.749981e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.749981e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.793297e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.801693e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.801693e+04 ) sec^-1 MeanMatrixElemValue = ( 4.214978e-01 +- 3.255521e-01 ) GeV^-4 -TOTAL : 0.947580 sec +TOTAL : 0.921472 sec INFO: No Floating Point Exceptions have been reported - 2,521,098,765 cycles # 2.651 GHz - 6,400,414,638 instructions # 2.54 insn per cycle - 0.951668346 seconds time elapsed + 2,523,779,273 cycles # 2.730 GHz + 6,401,399,707 instructions # 2.54 insn per cycle + 0.925110369 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11021) (512y: 43) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --common OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:COMMON+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.444514e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.449851e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.449851e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.398357e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.403401e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.403401e+04 ) sec^-1 MeanMatrixElemValue = ( 4.214981e-01 +- 3.255523e-01 ) GeV^-4 -TOTAL : 1.141729 sec +TOTAL : 1.179617 sec INFO: No Floating Point Exceptions have been reported - 2,071,860,072 cycles # 1.809 GHz - 3,300,448,625 instructions # 1.59 insn per cycle - 1.145827411 seconds time elapsed + 2,071,965,297 cycles # 1.751 GHz + 3,301,502,867 instructions # 1.59 insn per cycle + 1.184374263 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2601) (512y: 46) (512z: 9605) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952779718007E-004 Relative difference = 4.194411063934945e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_curhst.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_curhst.txt index 5594b3833..71166778f 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_curhst.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_curhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:53:13 +DATE: 2024-09-15_11:56:57 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.515702e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.552924e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.556552e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.530906e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.566446e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.569964e+05 ) sec^-1 MeanMatrixElemValue = ( 4.059596e+00 +- 2.368053e+00 ) GeV^-4 -TOTAL : 0.474495 sec +TOTAL : 0.476038 sec INFO: No Floating Point Exceptions have been reported - 2,011,973,393 cycles # 2.920 GHz - 3,012,287,196 instructions # 1.50 insn per cycle - 0.746226316 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst + 1,985,362,661 cycles # 2.871 GHz + 2,993,731,363 instructions # 1.51 insn per cycle + 0.748126319 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --curhst ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.157102e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.219957e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.222675e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.141583e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.198514e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.201079e+05 ) sec^-1 MeanMatrixElemValue = ( 6.664703e+00 +- 5.072736e+00 ) GeV^-4 -TOTAL : 1.819017 sec +TOTAL : 1.826652 sec INFO: No Floating Point Exceptions have been reported - 6,066,507,433 cycles # 2.960 GHz - 12,322,393,310 instructions # 2.03 insn per cycle - 2.106524554 seconds time elapsed + 5,952,227,239 cycles # 2.897 GHz + 12,995,171,990 instructions # 2.18 insn per cycle + 2.112711437 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.960123e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.961113e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.961113e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.933291e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.934237e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.934237e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060121e+00 +- 2.367902e+00 ) GeV^-4 -TOTAL : 8.372365 sec +TOTAL : 8.487946 sec INFO: No Floating Point Exceptions have been reported - 24,913,204,556 cycles # 2.975 GHz - 79,109,275,563 instructions # 3.18 insn per cycle - 8.376463077 seconds time elapsed + 24,924,562,928 cycles # 2.936 GHz + 79,109,269,886 instructions # 3.17 insn per cycle + 8.491506444 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274863312764526E-004 Relative difference = 4.998523613136231e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.100093e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.113139e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.113139e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.966222e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.978443e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.978443e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060119e+00 +- 2.367901e+00 ) GeV^-4 -TOTAL : 2.314710 sec +TOTAL : 2.359225 sec INFO: No Floating Point Exceptions have been reported - 6,539,620,343 cycles # 2.821 GHz - 20,270,856,622 instructions # 3.10 insn per cycle - 2.318690633 seconds time elapsed + 6,526,176,570 cycles # 2.763 GHz + 20,269,541,830 instructions # 3.11 insn per cycle + 2.362842375 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13779) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861442972011E-004 Relative difference = 2.1772539563413118e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.634403e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.641056e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.641056e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.543496e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.549592e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.549592e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 1.008306 sec +TOTAL : 1.067538 sec INFO: No Floating Point Exceptions have been reported - 2,848,061,854 cycles # 2.816 GHz - 7,066,418,028 instructions # 2.48 insn per cycle - 1.012267305 seconds time elapsed + 2,860,867,267 cycles # 2.672 GHz + 7,065,461,760 instructions # 2.47 insn per cycle + 1.071393478 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12055) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.832427e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.840853e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.840853e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.800483e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.808998e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.808998e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 0.899982 sec +TOTAL : 0.915759 sec INFO: No Floating Point Exceptions have been reported - 2,519,286,089 cycles # 2.789 GHz - 6,403,779,811 instructions # 2.54 insn per cycle - 0.904006492 seconds time elapsed + 2,516,887,683 cycles # 2.739 GHz + 6,403,177,488 instructions # 2.54 insn per cycle + 0.919482910 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11021) (512y: 43) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --curhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.443265e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.448590e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.448590e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.400235e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.405247e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.405247e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060562e+00 +- 2.367612e+00 ) GeV^-4 -TOTAL : 1.141808 sec +TOTAL : 1.176437 sec INFO: No Floating Point Exceptions have been reported - 2,068,467,128 cycles # 1.806 GHz - 3,304,001,462 instructions # 1.60 insn per cycle - 1.145999074 seconds time elapsed + 2,065,991,158 cycles # 1.752 GHz + 3,303,729,120 instructions # 1.60 insn per cycle + 1.180108788 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2601) (512y: 46) (512z: 9605) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952779718007E-004 Relative difference = 4.194411063934945e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_rmbhst.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_rmbhst.txt index 2c8782ca4..dd6ac1052 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_rmbhst.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0_rmbhst.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,76 +11,76 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:50:29 +DATE: 2024-09-15_11:54:10 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.073163e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.551560e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.555538e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.065242e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.543001e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.546426e+05 ) sec^-1 MeanMatrixElemValue = ( 4.048178e+00 +- 2.364571e+00 ) GeV^-4 -TOTAL : 0.478101 sec +TOTAL : 0.481262 sec INFO: No Floating Point Exceptions have been reported - 2,015,805,791 cycles # 2.914 GHz - 3,037,316,901 instructions # 1.51 insn per cycle - 0.749509646 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst + 1,996,897,335 cycles # 2.872 GHz + 2,970,634,149 instructions # 1.49 insn per cycle + 0.754034663 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --rmbhst WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --rmbhst OMP= WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.119461e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.190458e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.193209e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.141287e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.200996e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.203446e+05 ) sec^-1 MeanMatrixElemValue = ( 6.641709e+00 +- 4.994248e+00 ) GeV^-4 -TOTAL : 1.896617 sec +TOTAL : 1.902964 sec INFO: No Floating Point Exceptions have been reported - 6,339,268,119 cycles # 2.968 GHz - 13,650,810,628 instructions # 2.15 insn per cycle - 2.193112785 seconds time elapsed + 6,190,673,302 cycles # 2.901 GHz + 13,306,269,630 instructions # 2.15 insn per cycle + 2.189368892 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -88,33 +88,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.974482e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.975454e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.975454e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.933487e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.934407e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.934407e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060121e+00 +- 2.367902e+00 ) GeV^-4 -TOTAL : 8.311393 sec +TOTAL : 8.487231 sec INFO: No Floating Point Exceptions have been reported - 24,932,671,724 cycles # 2.999 GHz - 79,109,238,941 instructions # 3.17 insn per cycle - 8.315386942 seconds time elapsed + 24,900,546,223 cycles # 2.933 GHz + 79,107,234,987 instructions # 3.18 insn per cycle + 8.490956598 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3572) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -122,31 +122,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274863312764526E-004 Relative difference = 4.998523613136231e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.101882e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.114594e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.114594e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.983704e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.996217e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.996217e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060119e+00 +- 2.367901e+00 ) GeV^-4 -TOTAL : 2.314306 sec +TOTAL : 2.353085 sec INFO: No Floating Point Exceptions have been reported - 6,536,135,374 cycles # 2.820 GHz - 20,272,209,719 instructions # 3.10 insn per cycle - 2.318509943 seconds time elapsed + 6,541,995,614 cycles # 2.777 GHz + 20,269,407,860 instructions # 3.10 insn per cycle + 2.356873297 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13779) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -154,31 +154,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861442972011E-004 Relative difference = 2.1772539563413118e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.623539e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.630403e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.630403e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.585450e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.591953e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.591953e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 1.015014 sec +TOTAL : 1.039372 sec INFO: No Floating Point Exceptions have been reported - 2,855,704,305 cycles # 2.804 GHz - 7,065,922,001 instructions # 2.47 insn per cycle - 1.019088436 seconds time elapsed + 2,850,375,088 cycles # 2.735 GHz + 7,065,899,998 instructions # 2.48 insn per cycle + 1.043028953 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12055) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -186,31 +186,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.834257e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.842711e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.842711e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.792341e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.800787e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.800787e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 0.899190 sec +TOTAL : 0.920003 sec INFO: No Floating Point Exceptions have been reported - 2,520,844,071 cycles # 2.793 GHz - 6,403,739,146 instructions # 2.54 insn per cycle - 0.903188458 seconds time elapsed + 2,517,551,147 cycles # 2.728 GHz + 6,403,207,803 instructions # 2.54 insn per cycle + 0.923687532 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11021) (512y: 43) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -218,31 +218,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271938174396888E-004 Relative difference = 2.7547150614455683e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 1 --rmbhst OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.454972e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.460357e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.460357e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.402198e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.407285e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.407285e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060562e+00 +- 2.367612e+00 ) GeV^-4 -TOTAL : 1.132255 sec +TOTAL : 1.174725 sec INFO: No Floating Point Exceptions have been reported - 2,069,344,265 cycles # 1.822 GHz - 3,303,922,317 instructions # 1.60 insn per cycle - 1.136365608 seconds time elapsed + 2,068,104,176 cycles # 1.756 GHz + 3,303,725,822 instructions # 1.60 insn per cycle + 1.178407380 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2601) (512y: 46) (512z: 9605) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -250,8 +250,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952779718007E-004 Relative difference = 4.194411063934945e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd1.txt index fc75544cb..0807d31ee 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:20:19 +DATE: 2024-09-15_11:17:26 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.514511e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.549897e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.553526e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.482391e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.527725e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.532031e+05 ) sec^-1 MeanMatrixElemValue = ( 4.059596e+00 +- 2.368053e+00 ) GeV^-4 -TOTAL : 0.491830 sec +TOTAL : 0.493760 sec INFO: No Floating Point Exceptions have been reported - 2,056,287,025 cycles # 2.911 GHz - 3,100,773,025 instructions # 1.51 insn per cycle - 0.767274646 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 + 2,047,228,800 cycles # 2.877 GHz + 3,039,242,832 instructions # 1.48 insn per cycle + 0.768472979 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.110886e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.165093e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.167444e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.102852e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.164567e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.167207e+05 ) sec^-1 MeanMatrixElemValue = ( 6.664703e+00 +- 5.072736e+00 ) GeV^-4 -TOTAL : 1.793509 sec +TOTAL : 1.802499 sec INFO: No Floating Point Exceptions have been reported - 6,014,561,793 cycles # 2.958 GHz - 11,881,033,580 instructions # 1.98 insn per cycle - 2.090194643 seconds time elapsed + 5,908,213,594 cycles # 2.909 GHz + 12,456,477,911 instructions # 2.11 insn per cycle + 2.093284072 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262667672387088E-004 Relative difference = 2.825534762507892e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.968566e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.969505e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.969505e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.936218e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.937180e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.937180e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060121e+00 +- 2.367902e+00 ) GeV^-4 -TOTAL : 8.335960 sec +TOTAL : 8.475402 sec INFO: No Floating Point Exceptions have been reported - 24,939,697,284 cycles # 2.991 GHz - 78,843,077,860 instructions # 3.16 insn per cycle - 8.339952201 seconds time elapsed + 24,949,332,764 cycles # 2.943 GHz + 78,839,555,653 instructions # 3.16 insn per cycle + 8.479529977 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3092) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627487e-04 Avg ME (F77/C++) = 6.6274866250177339E-004 Relative difference = 5.65798569465384e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.281829e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.295515e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.295515e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.122699e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.135567e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.135567e+03 ) sec^-1 MeanMatrixElemValue = ( 4.060119e+00 +- 2.367901e+00 ) GeV^-4 -TOTAL : 2.256952 sec +TOTAL : 2.306947 sec INFO: No Floating Point Exceptions have been reported - 6,466,466,189 cycles # 2.861 GHz - 20,229,917,334 instructions # 3.13 insn per cycle - 2.261129242 seconds time elapsed + 6,466,639,499 cycles # 2.800 GHz + 20,230,851,658 instructions # 3.13 insn per cycle + 2.310638118 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13491) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274861448331612E-004 Relative difference = 2.1853408865157068e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.549288e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.555397e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.555397e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.507818e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.513887e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.513887e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 1.063285 sec +TOTAL : 1.092466 sec INFO: No Floating Point Exceptions have been reported - 2,979,164,688 cycles # 2.793 GHz - 7,206,814,892 instructions # 2.42 insn per cycle - 1.067401576 seconds time elapsed + 2,980,915,950 cycles # 2.722 GHz + 7,206,628,057 instructions # 2.42 insn per cycle + 1.096222389 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:12437) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271939668088170E-004 Relative difference = 5.008331292535666e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.759679e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.767582e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.767582e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.724603e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.732183e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.732183e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060560e+00 +- 2.367611e+00 ) GeV^-4 -TOTAL : 0.936636 sec +TOTAL : 0.955874 sec INFO: No Floating Point Exceptions have been reported - 2,613,305,137 cycles # 2.780 GHz - 6,544,993,852 instructions # 2.50 insn per cycle - 0.940671045 seconds time elapsed + 2,613,667,112 cycles # 2.726 GHz + 6,544,516,026 instructions # 2.50 insn per cycle + 0.959652526 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11449) (512y: 26) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627194e-04 Avg ME (F77/C++) = 6.6271939668088170E-004 Relative difference = 5.008331292535666e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.401401e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.406341e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.406341e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.352025e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.356715e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.356715e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060562e+00 +- 2.367612e+00 ) GeV^-4 -TOTAL : 1.175223 sec +TOTAL : 1.218129 sec INFO: No Floating Point Exceptions have been reported - 2,142,034,864 cycles # 1.818 GHz - 3,462,437,313 instructions # 1.62 insn per cycle - 1.179316947 seconds time elapsed + 2,137,040,914 cycles # 1.750 GHz + 3,460,849,319 instructions # 1.62 insn per cycle + 1.221974093 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3037) (512y: 25) (512z: 9677) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627195e-04 Avg ME (F77/C++) = 6.6271952032316561E-004 Relative difference = 3.066631594207157e-08 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd0.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd0.txt index bd734c798..507a64eed 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:37:31 +DATE: 2024-09-15_11:39:16 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.598056e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.633275e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.637037e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.567838e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.605874e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.609566e+05 ) sec^-1 MeanMatrixElemValue = ( 4.059597e+00 +- 2.368053e+00 ) GeV^-4 -TOTAL : 0.493073 sec +TOTAL : 0.496412 sec INFO: No Floating Point Exceptions have been reported - 2,074,178,646 cycles # 2.923 GHz - 3,133,020,237 instructions # 1.51 insn per cycle - 0.769870120 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 64 256 1 + 2,051,587,227 cycles # 2.873 GHz + 3,025,794,403 instructions # 1.47 insn per cycle + 0.774558823 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.631649e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.697107e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.700087e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.651284e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.721094e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.724249e+05 ) sec^-1 MeanMatrixElemValue = ( 6.664703e+00 +- 5.072736e+00 ) GeV^-4 -TOTAL : 1.730123 sec +TOTAL : 1.731680 sec INFO: No Floating Point Exceptions have been reported - 5,836,756,305 cycles # 2.975 GHz - 12,510,459,982 instructions # 2.14 insn per cycle - 2.018656217 seconds time elapsed + 5,770,677,421 cycles # 2.916 GHz + 12,010,283,008 instructions # 2.08 insn per cycle + 2.035197700 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262669162351490E-004 Relative difference = 2.8232862531213374e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl1_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl1_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 5.686722e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.687531e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.687531e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.459828e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.460600e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.460600e+02 ) sec^-1 MeanMatrixElemValue = ( 4.059969e+00 +- 2.367799e+00 ) GeV^-4 -TOTAL : 28.844831 sec +TOTAL : 30.042280 sec INFO: No Floating Point Exceptions have been reported - 86,631,947,563 cycles # 3.003 GHz - 135,663,970,094 instructions # 1.57 insn per cycle - 28.848826071 seconds time elapsed + 86,122,252,676 cycles # 2.867 GHz + 135,657,307,138 instructions # 1.58 insn per cycle + 30.046456599 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:15856) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627535e-04 Avg ME (F77/C++) = 6.6275349717465765E-004 Relative difference = 4.26303654465793e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.982423e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.994855e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.994855e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.672428e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.686393e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.686393e+03 ) sec^-1 MeanMatrixElemValue = ( 4.059962e+00 +- 2.367792e+00 ) GeV^-4 -TOTAL : 2.353688 sec +TOTAL : 2.462988 sec INFO: No Floating Point Exceptions have been reported - 6,754,455,687 cycles # 2.866 GHz - 19,356,639,694 instructions # 2.87 insn per cycle - 2.357792657 seconds time elapsed + 6,758,193,786 cycles # 2.742 GHz + 19,357,772,182 instructions # 2.86 insn per cycle + 2.467248153 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:69591) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274862748188362E-004 Relative difference = 4.14665283800746e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.465272e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.470907e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.470907e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.362305e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.367046e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.367046e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060903e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 1.124213 sec +TOTAL : 1.208685 sec INFO: No Floating Point Exceptions have been reported - 3,168,613,598 cycles # 2.810 GHz - 6,792,791,682 instructions # 2.14 insn per cycle - 1.128353409 seconds time elapsed + 3,166,621,827 cycles # 2.612 GHz + 6,792,444,940 instructions # 2.15 insn per cycle + 1.212802697 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:49012) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627273e-04 Avg ME (F77/C++) = 6.6272731568543797E-004 Relative difference = 2.3668012430631962e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.761149e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.768816e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.768816e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.652877e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.659885e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.659885e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060903e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 0.936182 sec +TOTAL : 0.997146 sec INFO: No Floating Point Exceptions have been reported - 2,624,003,917 cycles # 2.793 GHz - 5,970,228,341 instructions # 2.28 insn per cycle - 0.940254225 seconds time elapsed + 2,625,468,482 cycles # 2.624 GHz + 5,970,509,824 instructions # 2.27 insn per cycle + 1.001249505 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:42601) (512y: 11) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627273e-04 Avg ME (F77/C++) = 6.6272731568543797E-004 Relative difference = 2.3668012430631962e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.450303e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.455467e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.455467e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.322992e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.327409e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.327409e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060905e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 1.136203 sec +TOTAL : 1.244528 sec INFO: No Floating Point Exceptions have been reported - 2,073,701,956 cycles # 1.820 GHz - 3,493,813,941 instructions # 1.68 insn per cycle - 1.140373665 seconds time elapsed + 2,076,691,772 cycles # 1.664 GHz + 3,494,505,327 instructions # 1.68 insn per cycle + 1.248709350 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 5207) (512y: 3) (512z:44836) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627275e-04 Avg ME (F77/C++) = 6.6272750237027223E-004 Relative difference = 3.5765412974815996e-09 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd1.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd1.txt index 84ffcded9..c027e7477 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_f_inl1_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:38:20 +DATE: 2024-09-15_11:40:08 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.587128e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.623135e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.626795e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.562972e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.598287e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.601913e+05 ) sec^-1 MeanMatrixElemValue = ( 4.059597e+00 +- 2.368053e+00 ) GeV^-4 -TOTAL : 0.490425 sec +TOTAL : 0.492421 sec INFO: No Floating Point Exceptions have been reported - 2,067,306,761 cycles # 2.921 GHz - 3,120,326,206 instructions # 1.51 insn per cycle - 0.767854438 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 64 256 1 + 2,010,223,902 cycles # 2.826 GHz + 3,031,193,233 instructions # 1.51 insn per cycle + 0.770287796 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.673672e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.739936e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.742910e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.689601e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.749985e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.752940e+05 ) sec^-1 MeanMatrixElemValue = ( 6.664703e+00 +- 5.072736e+00 ) GeV^-4 -TOTAL : 1.727194 sec +TOTAL : 1.732807 sec INFO: No Floating Point Exceptions have been reported - 5,838,535,470 cycles # 2.981 GHz - 11,756,766,439 instructions # 2.01 insn per cycle - 2.016509360 seconds time elapsed + 5,640,346,322 cycles # 2.872 GHz + 11,210,275,869 instructions # 1.99 insn per cycle + 2.022037581 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_f_inl1_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626454e-04 Avg ME (F77/GPU) = 6.6262669162351490E-004 Relative difference = 2.8232862531213374e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl1_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_f_inl1_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 5.753740e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.754563e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.754563e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.446094e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.446837e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.446837e+02 ) sec^-1 MeanMatrixElemValue = ( 4.059969e+00 +- 2.367799e+00 ) GeV^-4 -TOTAL : 28.508335 sec +TOTAL : 30.118401 sec INFO: No Floating Point Exceptions have been reported - 85,830,228,914 cycles # 3.011 GHz - 135,366,257,259 instructions # 1.58 insn per cycle - 28.512429190 seconds time elapsed + 86,113,084,692 cycles # 2.859 GHz + 135,363,065,912 instructions # 1.57 insn per cycle + 30.122446956 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:15471) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627535e-04 Avg ME (F77/C++) = 6.6275349662128086E-004 Relative difference = 5.098002770919431e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.811935e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.824056e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.824056e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.516652e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.527742e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.527742e+03 ) sec^-1 MeanMatrixElemValue = ( 4.059962e+00 +- 2.367792e+00 ) GeV^-4 -TOTAL : 2.412491 sec +TOTAL : 2.521798 sec INFO: No Floating Point Exceptions have been reported - 6,846,250,673 cycles # 2.834 GHz - 19,407,013,482 instructions # 2.83 insn per cycle - 2.416838266 seconds time elapsed + 6,856,870,344 cycles # 2.715 GHz + 19,407,796,379 instructions # 2.83 insn per cycle + 2.529187527 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:69622) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627486e-04 Avg ME (F77/C++) = 6.6274862799683282E-004 Relative difference = 4.2243518621014775e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.495437e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.501066e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.501066e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.378784e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.383778e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.383778e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060903e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 1.101526 sec +TOTAL : 1.194647 sec INFO: No Floating Point Exceptions have been reported - 3,103,372,858 cycles # 2.809 GHz - 6,715,804,215 instructions # 2.16 insn per cycle - 1.105678914 seconds time elapsed + 3,106,911,149 cycles # 2.593 GHz + 6,716,375,817 instructions # 2.16 insn per cycle + 1.199018593 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:47699) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627273e-04 Avg ME (F77/C++) = 6.6272731623419345E-004 Relative difference = 2.449603850635964e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.771188e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.779181e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.779181e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.633831e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.642301e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.642301e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060903e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 0.930819 sec +TOTAL : 1.009236 sec INFO: No Floating Point Exceptions have been reported - 2,625,713,520 cycles # 2.810 GHz - 5,968,739,740 instructions # 2.27 insn per cycle - 0.934943696 seconds time elapsed + 2,628,290,758 cycles # 2.601 GHz + 5,969,462,739 instructions # 2.27 insn per cycle + 1.017917591 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:41882) (512y: 13) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627273e-04 Avg ME (F77/C++) = 6.6272731623419345E-004 Relative difference = 2.449603850635964e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=1] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.430515e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.435702e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.435702e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.325974e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.330533e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.330533e+04 ) sec^-1 MeanMatrixElemValue = ( 4.060905e+00 +- 2.367377e+00 ) GeV^-4 -TOTAL : 1.151409 sec +TOTAL : 1.242092 sec INFO: No Floating Point Exceptions have been reported - 2,066,103,190 cycles # 1.789 GHz - 3,487,311,772 instructions # 1.69 insn per cycle - 1.155609949 seconds time elapsed + 2,077,381,824 cycles # 1.674 GHz + 3,490,865,426 instructions # 1.68 insn per cycle + 1.248861709 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4171) (512y: 4) (512z:44487) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_f_inl1_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.627275e-04 Avg ME (F77/C++) = 6.6272750247886592E-004 Relative difference = 3.740400032174438e-09 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd0.txt index 2f68bb4a8..f1d40dff2 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:20:46 +DATE: 2024-09-15_11:17:52 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.331621e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.355030e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.356680e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.307071e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.337162e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.339154e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.530458 sec +TOTAL : 0.532508 sec INFO: No Floating Point Exceptions have been reported - 2,214,937,387 cycles # 2.872 GHz - 3,503,262,390 instructions # 1.58 insn per cycle - 0.829415308 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 + 2,203,526,312 cycles # 2.869 GHz + 3,467,986,959 instructions # 1.57 insn per cycle + 0.824379177 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.144030e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.171626e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.172804e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.133497e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.164330e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.165560e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.032896 sec +TOTAL : 3.045403 sec INFO: No Floating Point Exceptions have been reported - 9,787,989,221 cycles # 2.968 GHz - 22,358,228,581 instructions # 2.28 insn per cycle - 3.355717561 seconds time elapsed + 9,651,769,916 cycles # 2.918 GHz + 21,560,396,285 instructions # 2.23 insn per cycle + 3.363407224 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266732376103494E-004 Relative difference = 2.659538381540814e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.889361e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.890286e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.890286e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.856718e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.857596e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.857596e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.686369 sec +TOTAL : 8.839571 sec INFO: No Floating Point Exceptions have been reported - 25,927,576,057 cycles # 2.984 GHz - 79,425,809,752 instructions # 3.06 insn per cycle - 8.690475608 seconds time elapsed + 25,916,613,183 cycles # 2.931 GHz + 79,423,792,934 instructions # 3.06 insn per cycle + 8.843857471 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4775) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731406016235E-004 Relative difference = 2.8059296349552523e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.578240e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.581401e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.581401e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.495399e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.498545e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.498545e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.589410 sec +TOTAL : 4.699126 sec INFO: No Floating Point Exceptions have been reported - 12,833,581,935 cycles # 2.794 GHz - 38,823,261,134 instructions # 3.03 insn per cycle - 4.593493589 seconds time elapsed + 12,847,395,150 cycles # 2.733 GHz + 38,826,102,030 instructions # 3.02 insn per cycle + 4.703180057 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:13173) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730246908442E-004 Relative difference = 2.98084507782618e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.161910e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.177971e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.177971e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.037182e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.053225e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.053225e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.015681 sec +TOTAL : 2.047520 sec INFO: No Floating Point Exceptions have been reported - 5,623,032,218 cycles # 2.785 GHz - 13,615,351,145 instructions # 2.42 insn per cycle - 2.019952518 seconds time elapsed + 5,598,661,180 cycles # 2.730 GHz + 13,618,631,873 instructions # 2.43 insn per cycle + 2.051512013 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11427) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.464776e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.487442e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.487442e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.221665e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.243251e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.243251e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.739023 sec +TOTAL : 1.785642 sec INFO: No Floating Point Exceptions have been reported - 4,862,882,649 cycles # 2.791 GHz - 12,296,492,579 instructions # 2.53 insn per cycle - 1.743291896 seconds time elapsed + 4,865,374,839 cycles # 2.720 GHz + 12,297,660,832 instructions # 2.53 insn per cycle + 1.789585857 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10331) (512y: 79) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.177088e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.189830e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.189830e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.872514e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.884400e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.884400e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.291509 sec +TOTAL : 2.393483 sec INFO: No Floating Point Exceptions have been reported - 4,173,466,182 cycles # 1.819 GHz - 6,390,838,755 instructions # 1.53 insn per cycle - 2.295964952 seconds time elapsed + 4,171,721,525 cycles # 1.741 GHz + 6,391,185,056 instructions # 1.53 insn per cycle + 2.397568985 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1980) (512y: 93) (512z: 9360) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 diff --git a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd1.txt index bb6eacdb6..ae3635632 100644 --- a/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg' -DATE: 2024-09-01_23:21:19 +DATE: 2024-09-15_11:18:27 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.322191e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.344102e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.345776e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.320961e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.350573e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.352533e+05 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 0.529512 sec +TOTAL : 0.532217 sec INFO: No Floating Point Exceptions have been reported - 2,233,296,216 cycles # 2.915 GHz - 3,529,609,506 instructions # 1.58 insn per cycle - 0.825080098 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 + 2,207,479,579 cycles # 2.873 GHz + 3,464,148,832 instructions # 1.57 insn per cycle + 0.824297603 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.141564e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.169144e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.170301e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.148990e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.180422e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.181658e+05 ) sec^-1 MeanMatrixElemValue = ( 6.665112e+00 +- 5.002651e+00 ) GeV^-4 -TOTAL : 3.033131 sec +TOTAL : 3.035739 sec INFO: No Floating Point Exceptions have been reported - 9,779,205,799 cycles # 2.967 GHz - 21,659,055,827 instructions # 2.21 insn per cycle - 3.355957763 seconds time elapsed + 9,612,803,881 cycles # 2.915 GHz + 20,074,302,744 instructions # 2.09 insn per cycle + 3.353532451 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 6.626675e-04 Avg ME (F77/GPU) = 6.6266732376103494E-004 Relative difference = 2.659538381540814e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.887290e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.888180e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.888180e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.831511e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.832364e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.832364e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 8.695848 sec +TOTAL : 8.961804 sec INFO: No Floating Point Exceptions have been reported - 25,991,391,295 cycles # 2.988 GHz - 79,451,765,257 instructions # 3.06 insn per cycle - 8.700070515 seconds time elapsed + 26,010,493,082 cycles # 2.902 GHz + 79,449,384,960 instructions # 3.05 insn per cycle + 8.965752302 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 4431) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266731406016235E-004 Relative difference = 2.8059296349552523e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.584459e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.587768e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.587768e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.477024e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.480127e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.480127e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 4.581005 sec +TOTAL : 4.723753 sec INFO: No Floating Point Exceptions have been reported - 12,823,284,183 cycles # 2.797 GHz - 38,780,792,036 instructions # 3.02 insn per cycle - 4.585213943 seconds time elapsed + 12,826,084,303 cycles # 2.714 GHz + 38,778,289,694 instructions # 3.02 insn per cycle + 4.727826379 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:12935) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730246908442E-004 Relative difference = 2.98084507782618e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.220702e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.236918e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.236918e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.051767e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.067821e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.067821e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.001136 sec +TOTAL : 2.043694 sec INFO: No Floating Point Exceptions have been reported - 5,586,247,922 cycles # 2.787 GHz - 13,732,848,224 instructions # 2.46 insn per cycle - 2.005304858 seconds time elapsed + 5,591,778,218 cycles # 2.733 GHz + 13,733,552,430 instructions # 2.46 insn per cycle + 2.047665232 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:11510) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 9.263881e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.285362e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.285362e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.123898e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.144357e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.144357e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 1.776462 sec +TOTAL : 1.804403 sec INFO: No Floating Point Exceptions have been reported - 4,951,429,315 cycles # 2.782 GHz - 12,423,212,120 instructions # 2.51 insn per cycle - 1.780606206 seconds time elapsed + 4,951,573,094 cycles # 2.739 GHz + 12,422,632,916 instructions # 2.51 insn per cycle + 1.808331695 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:10322) (512y: 239) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.149223e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.161842e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.161842e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.884699e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.896731e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.896731e+03 ) sec^-1 MeanMatrixElemValue = ( 4.063123e+00 +- 2.368970e+00 ) GeV^-4 -TOTAL : 2.300056 sec +TOTAL : 2.389141 sec INFO: No Floating Point Exceptions have been reported - 4,175,293,644 cycles # 1.813 GHz - 6,494,363,004 instructions # 1.56 insn per cycle - 2.304264144 seconds time elapsed + 4,181,828,175 cycles # 1.750 GHz + 6,496,177,989 instructions # 1.55 insn per cycle + 2.393377398 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1803) (512y: 191) (512z: 9369) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 123 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 123 channels { 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32, 17 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 6.626675e-04 Avg ME (F77/C++) = 6.6266730409276857E-004 Relative difference = 2.956342832710188e-07 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0.txt index 98ba462e3..407fbbe6c 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:23:11 +DATE: 2024-09-15_11:20:21 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.059306e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.059673e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.059842e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.059284e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.059685e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.059813e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 2.431556 sec +TOTAL : 2.451621 sec INFO: No Floating Point Exceptions have been reported - 8,193,040,145 cycles # 2.976 GHz - 18,582,642,986 instructions # 2.27 insn per cycle - 2.812032026 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 + 8,080,887,114 cycles # 2.907 GHz + 16,734,437,330 instructions # 2.07 insn per cycle + 2.836211679 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.218449e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.220375e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.220612e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.254596e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.256737e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.256950e+03 ) sec^-1 MeanMatrixElemValue = ( 1.856249e-04 +- 8.329951e-05 ) GeV^-6 -TOTAL : 4.004890 sec +TOTAL : 4.020216 sec INFO: No Floating Point Exceptions have been reported - 12,865,885,820 cycles # 2.967 GHz - 28,902,839,656 instructions # 2.25 insn per cycle - 4.392213239 seconds time elapsed + 12,719,492,672 cycles # 2.923 GHz + 29,448,097,640 instructions # 2.32 insn per cycle + 4.407436029 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.872263e-03 Avg ME (F77/GPU) = 9.8722595284406640E-003 Relative difference = 3.5164777671934515e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 7.740296e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.740516e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.740516e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.610103e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.610301e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.610301e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 6.825078 sec +TOTAL : 6.935255 sec INFO: No Floating Point Exceptions have been reported - 19,056,883,522 cycles # 2.791 GHz - 53,906,242,080 instructions # 2.83 insn per cycle - 6.829199798 seconds time elapsed + 18,974,774,871 cycles # 2.735 GHz + 53,899,721,094 instructions # 2.84 insn per cycle + 6.939338261 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:32424) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.611722e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.611814e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.611814e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.579226e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.579318e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.579318e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 3.278065 sec +TOTAL : 3.345304 sec INFO: No Floating Point Exceptions have been reported - 9,778,535,399 cycles # 2.980 GHz - 27,150,865,076 instructions # 2.78 insn per cycle - 3.282250786 seconds time elapsed + 9,800,813,517 cycles # 2.927 GHz + 27,149,189,789 instructions # 2.77 insn per cycle + 3.349514409 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:96492) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.476638e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.477048e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.477048e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.366336e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.366803e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.366803e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.520727 sec +TOTAL : 1.570292 sec INFO: No Floating Point Exceptions have been reported - 4,244,700,698 cycles # 2.785 GHz - 9,590,825,029 instructions # 2.26 insn per cycle - 1.524880781 seconds time elapsed + 4,287,053,926 cycles # 2.724 GHz + 9,590,127,631 instructions # 2.24 insn per cycle + 1.574599019 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:84961) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.994080e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.994623e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.994623e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.904765e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.905290e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.905290e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.323946 sec +TOTAL : 1.353979 sec INFO: No Floating Point Exceptions have been reported - 3,716,328,988 cycles # 2.800 GHz - 8,515,493,481 instructions # 2.29 insn per cycle - 1.328049109 seconds time elapsed + 3,709,436,689 cycles # 2.733 GHz + 8,514,247,183 instructions # 2.30 insn per cycle + 1.357880276 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:80609) (512y: 89) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.542686e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.543288e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.543288e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.407683e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.408196e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.408196e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.492969 sec +TOTAL : 1.552623 sec INFO: No Floating Point Exceptions have been reported - 2,695,876,323 cycles # 1.802 GHz - 4,282,247,178 instructions # 1.59 insn per cycle - 1.497260293 seconds time elapsed + 2,699,560,921 cycles # 1.736 GHz + 4,280,862,154 instructions # 1.59 insn per cycle + 1.556608026 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2853) (512y: 103) (512z:79114) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0_bridge.txt index 717f8886d..e03215103 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,11 +21,11 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:45:42 +DATE: 2024-09-15_11:49:15 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -34,17 +34,17 @@ WARNING! Set grid in Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gp Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.053935e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.056881e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.056881e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.054597e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.057500e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.057500e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 2.379946 sec +TOTAL : 2.436820 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 8,083,288,425 cycles # 2.992 GHz - 17,108,705,420 instructions # 2.12 insn per cycle - 2.760730215 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 --bridge + 8,044,156,582 cycles # 2.913 GHz + 18,167,469,518 instructions # 2.26 insn per cycle + 2.819990438 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gputhreads=256) @@ -52,7 +52,7 @@ WARNING! Set grid in Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gp ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -61,18 +61,18 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.231350e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.265023e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.265023e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.188185e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.221546e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.221546e+03 ) sec^-1 MeanMatrixElemValue = ( 1.856249e-04 +- 8.329951e-05 ) GeV^-6 -TOTAL : 3.986993 sec +TOTAL : 4.024442 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 12,934,982,025 cycles # 2.992 GHz - 29,294,622,576 instructions # 2.26 insn per cycle - 4.378595360 seconds time elapsed + 12,704,137,155 cycles # 2.918 GHz + 27,467,799,669 instructions # 2.16 insn per cycle + 4.411963692 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -80,35 +80,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.872263e-03 Avg ME (F77/GPU) = 9.8722595284406640E-003 Relative difference = 3.5164777671934515e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 7.734772e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.735047e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.735047e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.352982e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.353176e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.353176e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 6.825716 sec +TOTAL : 7.182913 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 19,050,334,983 cycles # 2.790 GHz - 53,904,991,030 instructions # 2.83 insn per cycle - 6.829977475 seconds time elapsed + 19,533,134,643 cycles # 2.719 GHz + 53,904,822,620 instructions # 2.76 insn per cycle + 7.186820393 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:32424) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -116,33 +116,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.615071e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.615160e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.615160e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.583220e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.583307e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.583307e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 3.270482 sec +TOTAL : 3.337581 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 9,810,845,524 cycles # 2.997 GHz - 27,153,154,462 instructions # 2.77 insn per cycle - 3.274772696 seconds time elapsed + 9,779,129,351 cycles # 2.927 GHz + 27,151,664,900 instructions # 2.78 insn per cycle + 3.341583664 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:96492) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -150,33 +150,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.459833e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.460241e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.460241e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.365450e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.365854e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.365854e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.527944 sec +TOTAL : 1.570834 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,289,516,676 cycles # 2.801 GHz - 9,592,867,163 instructions # 2.24 insn per cycle - 1.532272856 seconds time elapsed + 4,275,074,655 cycles # 2.716 GHz + 9,592,294,661 instructions # 2.24 insn per cycle + 1.574792391 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:84961) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -184,33 +184,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.939776e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.940326e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.940326e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.876513e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.877048e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.877048e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.342790 sec +TOTAL : 1.364090 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 3,731,950,548 cycles # 2.772 GHz - 8,517,158,155 instructions # 2.28 insn per cycle - 1.347148638 seconds time elapsed + 3,720,013,902 cycles # 2.721 GHz + 8,517,094,572 instructions # 2.29 insn per cycle + 1.368386654 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:80609) (512y: 89) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -218,33 +218,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.477757e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.478322e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.478322e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.420108e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.420617e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.420617e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.519990 sec +TOTAL : 1.546895 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,699,759,683 cycles # 1.772 GHz - 4,284,442,288 instructions # 1.59 insn per cycle - 1.524543784 seconds time elapsed + 2,698,104,238 cycles # 1.741 GHz + 4,283,566,876 instructions # 1.59 insn per cycle + 1.551097954 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2853) (512y: 103) (512z:79114) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -252,8 +252,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd1.txt index 1483c9bce..71b1803a4 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:24:38 +DATE: 2024-09-15_11:21:49 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.058852e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.059241e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.059373e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.055075e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.055529e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.055650e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 2.431399 sec +TOTAL : 2.454190 sec INFO: No Floating Point Exceptions have been reported - 8,193,686,544 cycles # 2.973 GHz - 18,087,344,365 instructions # 2.21 insn per cycle - 2.812916099 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 1 + 8,101,270,896 cycles # 2.912 GHz + 18,320,414,768 instructions # 2.26 insn per cycle + 2.837550341 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.226524e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.228420e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.228644e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.224205e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.226444e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.226692e+03 ) sec^-1 MeanMatrixElemValue = ( 1.856249e-04 +- 8.329951e-05 ) GeV^-6 -TOTAL : 4.008011 sec +TOTAL : 4.029157 sec INFO: No Floating Point Exceptions have been reported - 12,900,895,160 cycles # 2.974 GHz - 30,531,158,775 instructions # 2.37 insn per cycle - 4.392074978 seconds time elapsed + 12,695,828,795 cycles # 2.910 GHz + 28,709,503,011 instructions # 2.26 insn per cycle + 4.420420636 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.872263e-03 Avg ME (F77/GPU) = 9.8722595284406640E-003 Relative difference = 3.5164777671934515e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 7.805727e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.805945e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.805945e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.201824e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.202080e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.202080e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 6.764030 sec +TOTAL : 6.438167 sec INFO: No Floating Point Exceptions have been reported - 18,779,280,912 cycles # 2.775 GHz - 53,933,449,541 instructions # 2.87 insn per cycle - 6.768170476 seconds time elapsed + 18,843,132,149 cycles # 2.926 GHz + 53,928,570,497 instructions # 2.86 insn per cycle + 6.442267111 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:32022) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.591597e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.591682e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.591682e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.562611e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.562704e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.562704e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 3.318241 sec +TOTAL : 3.380180 sec INFO: No Floating Point Exceptions have been reported - 9,916,194,875 cycles # 2.985 GHz - 27,130,313,114 instructions # 2.74 insn per cycle - 3.322321674 seconds time elapsed + 9,918,861,148 cycles # 2.932 GHz + 27,128,280,341 instructions # 2.74 insn per cycle + 3.383996000 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:96368) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285514851E-003 Relative difference = 3.5163655122073967e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.453253e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.453647e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.453647e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.368711e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.369114e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.369114e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.529460 sec +TOTAL : 1.568940 sec INFO: No Floating Point Exceptions have been reported - 4,280,208,349 cycles # 2.792 GHz - 9,585,335,411 instructions # 2.24 insn per cycle - 1.533657128 seconds time elapsed + 4,289,720,535 cycles # 2.728 GHz + 9,584,928,513 instructions # 2.23 insn per cycle + 1.573132113 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:84968) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.973507e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.974053e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.974053e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.874256e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.874798e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.874798e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.330487 sec +TOTAL : 1.364932 sec INFO: No Floating Point Exceptions have been reported - 3,719,620,826 cycles # 2.788 GHz - 8,507,837,533 instructions # 2.29 insn per cycle - 1.334658974 seconds time elapsed + 3,728,944,037 cycles # 2.726 GHz + 8,507,330,131 instructions # 2.28 insn per cycle + 1.368786926 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:80632) (512y: 239) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.357138e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.357653e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.357653e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.414224e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.414743e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.414743e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 1.572289 sec +TOTAL : 1.549013 sec INFO: No Floating Point Exceptions have been reported - 2,699,107,966 cycles # 1.713 GHz - 4,281,647,123 instructions # 1.59 insn per cycle - 1.576538172 seconds time elapsed + 2,698,122,905 cycles # 1.738 GHz + 4,280,648,246 instructions # 1.59 insn per cycle + 1.553090413 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2690) (512y: 185) (512z:79098) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595285411531E-003 Relative difference = 3.516375977906115e-07 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0.txt index 09bdb5cca..26694465d 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:26:04 +DATE: 2024-09-15_11:23:17 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.208371e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.209254e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.209558e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.208704e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.209632e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.209859e+02 ) sec^-1 MeanMatrixElemValue = ( 1.186984e-05 +- 9.824899e-06 ) GeV^-6 -TOTAL : 1.739489 sec +TOTAL : 1.761935 sec INFO: No Floating Point Exceptions have been reported - 5,891,365,145 cycles # 2.944 GHz - 12,121,835,329 instructions # 2.06 insn per cycle - 2.057320302 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 + 5,908,004,381 cycles # 2.901 GHz + 11,686,361,328 instructions # 1.98 insn per cycle + 2.093948305 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.128447e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.128992e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.129117e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.102338e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.102897e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.103014e+04 ) sec^-1 MeanMatrixElemValue = ( 1.856829e-04 +- 8.333437e-05 ) GeV^-6 -TOTAL : 2.049663 sec +TOTAL : 2.075560 sec INFO: No Floating Point Exceptions have been reported - 6,859,898,495 cycles # 2.967 GHz - 15,045,871,459 instructions # 2.19 insn per cycle - 2.368699830 seconds time elapsed + 6,795,219,354 cycles # 2.902 GHz + 14,967,758,240 instructions # 2.20 insn per cycle + 2.398428041 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.849635e-03 Avg ME (F77/GPU) = 9.8712451931260159E-003 Relative difference = 0.0021940095370046923 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 8.700551e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.700826e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.700826e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.563117e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.563375e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.563375e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825040e-06 ) GeV^-6 -TOTAL : 6.069647 sec +TOTAL : 6.168224 sec INFO: No Floating Point Exceptions have been reported - 18,130,580,813 cycles # 2.986 GHz - 53,910,417,290 instructions # 2.97 insn per cycle - 6.073649498 seconds time elapsed + 18,106,019,929 cycles # 2.934 GHz + 53,907,716,361 instructions # 2.98 insn per cycle + 6.172403776 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:20141) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847961e-03 Avg ME (F77/C++) = 9.8479612087551509E-003 Relative difference = 2.119780432912131e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.447845e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.448292e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.448292e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.366569e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.366962e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.366962e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825037e-06 ) GeV^-6 -TOTAL : 1.533158 sec +TOTAL : 1.570259 sec INFO: No Floating Point Exceptions have been reported - 4,594,810,836 cycles # 2.990 GHz - 13,807,588,425 instructions # 3.01 insn per cycle - 1.537438030 seconds time elapsed + 4,597,646,888 cycles # 2.923 GHz + 13,807,163,752 instructions # 3.00 insn per cycle + 1.574045592 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:97016) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847955e-03 Avg ME (F77/C++) = 9.8479546896367235E-003 Relative difference = 3.1515505172940424e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.958378e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.960444e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.960444e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.801272e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.802916e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.802916e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.760583 sec +TOTAL : 0.778379 sec INFO: No Floating Point Exceptions have been reported - 2,125,857,620 cycles # 2.782 GHz - 4,836,877,931 instructions # 2.28 insn per cycle - 0.764668733 seconds time elapsed + 2,130,043,758 cycles # 2.726 GHz + 4,836,599,174 instructions # 2.27 insn per cycle + 0.782206721 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:85494) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091246E-003 Relative difference = 1.8588029579156084e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.833177e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.835234e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.835234e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.682520e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.684604e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.684604e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.675768 sec +TOTAL : 0.688940 sec INFO: No Floating Point Exceptions have been reported - 1,884,867,686 cycles # 2.775 GHz - 4,291,429,103 instructions # 2.28 insn per cycle - 0.679860499 seconds time elapsed + 1,884,507,725 cycles # 2.723 GHz + 4,290,819,235 instructions # 2.28 insn per cycle + 0.692749981 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:81185) (512y: 44) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091246E-003 Relative difference = 1.8588029579156084e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.899775e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.902123e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.902123e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.875530e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.877565e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.877565e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826771e-06 ) GeV^-6 -TOTAL : 0.767901 sec +TOTAL : 0.770700 sec INFO: No Floating Point Exceptions have been reported - 1,356,316,269 cycles # 1.758 GHz - 2,162,893,262 instructions # 1.59 insn per cycle - 0.772192163 seconds time elapsed + 1,352,613,897 cycles # 1.747 GHz + 2,162,405,721 instructions # 1.60 insn per cycle + 0.774947088 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3479) (512y: 47) (512z:79330) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892981e-03 Avg ME (F77/C++) = 9.8929811982676284E-003 Relative difference = 2.004124217057488e-08 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0_bridge.txt index 51152ded1..8e4037314 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,11 +21,11 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:47:09 +DATE: 2024-09-15_11:50:44 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -34,17 +34,17 @@ WARNING! Set grid in Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gp Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.301300e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.306154e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.306154e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.261572e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.268191e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.268191e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187093e-05 +- 9.825663e-06 ) GeV^-6 -TOTAL : 1.672870 sec +TOTAL : 1.738260 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 5,721,818,888 cycles # 2.961 GHz - 12,395,752,294 instructions # 2.17 insn per cycle - 1.988963755 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 --bridge + 5,820,188,860 cycles # 2.913 GHz + 12,502,480,728 instructions # 2.15 insn per cycle + 2.056507800 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gputhreads=256) @@ -52,7 +52,7 @@ WARNING! Set grid in Bridge (nevt=256, gpublocks=1, gputhreads=256, gpublocks*gp ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -61,18 +61,18 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.121175e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.132575e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.132575e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.148842e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.160493e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.160493e+04 ) sec^-1 MeanMatrixElemValue = ( 1.856440e-04 +- 8.331091e-05 ) GeV^-6 -TOTAL : 2.019350 sec +TOTAL : 2.045649 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 6,564,670,149 cycles # 2.877 GHz - 14,591,387,808 instructions # 2.22 insn per cycle - 2.337966336 seconds time elapsed + 6,753,066,902 cycles # 2.917 GHz + 14,813,097,918 instructions # 2.19 insn per cycle + 2.374262766 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -80,35 +80,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.849635e-03 Avg ME (F77/GPU) = 9.8712451931260159E-003 Relative difference = 0.0021940095370046923 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 8.683425e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.683681e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.683681e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.502637e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.502889e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.502889e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825040e-06 ) GeV^-6 -TOTAL : 6.082069 sec +TOTAL : 6.211468 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 18,173,296,870 cycles # 2.987 GHz - 53,912,583,820 instructions # 2.97 insn per cycle - 6.086323477 seconds time elapsed + 18,143,644,137 cycles # 2.921 GHz + 53,909,939,321 instructions # 2.97 insn per cycle + 6.215559174 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:20141) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -116,33 +116,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847961e-03 Avg ME (F77/C++) = 9.8479612087551509E-003 Relative difference = 2.119780432912131e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.446030e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.446471e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.446471e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.339632e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.340031e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.340031e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825037e-06 ) GeV^-6 -TOTAL : 1.534197 sec +TOTAL : 1.583158 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,592,088,424 cycles # 2.986 GHz - 13,809,471,792 instructions # 3.01 insn per cycle - 1.538429740 seconds time elapsed + 4,644,642,721 cycles # 2.928 GHz + 13,808,855,992 instructions # 2.97 insn per cycle + 1.587116749 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:97016) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -150,33 +150,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847955e-03 Avg ME (F77/C++) = 9.8479546896367235E-003 Relative difference = 3.1515505172940424e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.989257e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.991152e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.991152e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.786207e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.787843e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.787843e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.757797 sec +TOTAL : 0.780530 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,125,674,277 cycles # 2.793 GHz - 4,839,269,663 instructions # 2.28 insn per cycle - 0.762099515 seconds time elapsed + 2,130,238,055 cycles # 2.718 GHz + 4,838,587,482 instructions # 2.27 insn per cycle + 0.784611119 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:85494) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -184,33 +184,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091246E-003 Relative difference = 1.8588029579156084e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.782488e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.784687e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.784687e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.698223e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.700507e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.700507e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.681843 sec +TOTAL : 0.688171 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,884,280,976 cycles # 2.749 GHz - 4,293,258,485 instructions # 2.28 insn per cycle - 0.686156926 seconds time elapsed + 1,885,276,472 cycles # 2.726 GHz + 4,293,094,440 instructions # 2.28 insn per cycle + 0.692122848 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:81185) (512y: 44) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -218,33 +218,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091246E-003 Relative difference = 1.8588029579156084e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=256) Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.037894e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.040203e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.040203e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.810636e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.812720e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.812720e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826771e-06 ) GeV^-6 -TOTAL : 0.753383 sec +TOTAL : 0.777981 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,356,538,183 cycles # 1.791 GHz - 2,164,775,306 instructions # 1.60 insn per cycle - 0.757910726 seconds time elapsed + 1,355,130,660 cycles # 1.735 GHz + 2,164,600,762 instructions # 1.60 insn per cycle + 0.782043846 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3479) (512y: 47) (512z:79330) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -252,8 +252,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892981e-03 Avg ME (F77/C++) = 9.8929811982676284E-003 Relative difference = 2.004124217057488e-08 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd1.txt index 65b406fa0..113bcaacf 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:27:06 +DATE: 2024-09-15_11:24:20 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.191607e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.192340e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.192663e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.202287e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.203031e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.203251e+02 ) sec^-1 MeanMatrixElemValue = ( 1.186984e-05 +- 9.824899e-06 ) GeV^-6 -TOTAL : 1.742189 sec +TOTAL : 1.759878 sec INFO: No Floating Point Exceptions have been reported - 5,932,372,302 cycles # 2.963 GHz - 12,508,103,447 instructions # 2.11 insn per cycle - 2.058857713 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 1 + 5,921,315,429 cycles # 2.907 GHz + 12,451,469,321 instructions # 2.10 insn per cycle + 2.095417433 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.133592e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.134143e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.134218e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.113173e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.113784e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.113870e+04 ) sec^-1 MeanMatrixElemValue = ( 1.856829e-04 +- 8.333437e-05 ) GeV^-6 -TOTAL : 2.056045 sec +TOTAL : 2.088774 sec INFO: No Floating Point Exceptions have been reported - 6,889,881,075 cycles # 2.974 GHz - 14,292,406,169 instructions # 2.07 insn per cycle - 2.373717598 seconds time elapsed + 6,829,574,271 cycles # 2.905 GHz + 14,898,722,914 instructions # 2.18 insn per cycle + 2.410171422 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.849635e-03 Avg ME (F77/GPU) = 9.8712451931260107E-003 Relative difference = 0.0021940095370041636 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 8.764150e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.764424e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.764424e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.526309e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.526569e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.526569e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825040e-06 ) GeV^-6 -TOTAL : 6.026782 sec +TOTAL : 6.192756 sec INFO: No Floating Point Exceptions have been reported - 18,051,302,313 cycles # 2.994 GHz - 53,897,977,148 instructions # 2.99 insn per cycle - 6.030777768 seconds time elapsed + 18,135,421,902 cycles # 2.927 GHz + 53,892,650,631 instructions # 2.97 insn per cycle + 6.196840431 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:20141) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847961e-03 Avg ME (F77/C++) = 9.8479612087572898E-003 Relative difference = 2.1198021522715588e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.471197e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.471611e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.471611e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.396709e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.397124e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.397124e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187013e-05 +- 9.825037e-06 ) GeV^-6 -TOTAL : 1.522952 sec +TOTAL : 1.556067 sec INFO: No Floating Point Exceptions have been reported - 4,568,290,742 cycles # 2.993 GHz - 13,800,705,057 instructions # 3.02 insn per cycle - 1.527092884 seconds time elapsed + 4,573,398,855 cycles # 2.934 GHz + 13,800,378,388 instructions # 3.02 insn per cycle + 1.559827589 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:96651) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.847955e-03 Avg ME (F77/C++) = 9.8479546896065809E-003 Relative difference = 3.151856596628469e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.916676e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.918574e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.918574e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.651495e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.653049e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.653049e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.765094 sec +TOTAL : 0.795401 sec INFO: No Floating Point Exceptions have been reported - 2,149,872,306 cycles # 2.797 GHz - 4,840,917,798 instructions # 2.25 insn per cycle - 0.769224783 seconds time elapsed + 2,148,860,867 cycles # 2.691 GHz + 4,840,602,339 instructions # 2.25 insn per cycle + 0.799229981 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:85884) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091923E-003 Relative difference = 1.85880227405429e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 7.862816e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.864916e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.864916e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.688407e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.690576e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.690576e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826767e-06 ) GeV^-6 -TOTAL : 0.673473 sec +TOTAL : 0.688541 sec INFO: No Floating Point Exceptions have been reported - 1,891,619,024 cycles # 2.794 GHz - 4,294,912,545 instructions # 2.27 insn per cycle - 0.677525045 seconds time elapsed + 1,890,706,185 cycles # 2.733 GHz + 4,294,394,779 instructions # 2.27 insn per cycle + 0.692328039 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:81725) (512y: 24) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892973e-03 Avg ME (F77/C++) = 9.8929728161091923E-003 Relative difference = 1.85880227405429e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.805387e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.807811e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.807811e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.826093e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.828148e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.828148e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187188e-05 +- 9.826771e-06 ) GeV^-6 -TOTAL : 0.778957 sec +TOTAL : 0.775828 sec INFO: No Floating Point Exceptions have been reported - 1,357,861,459 cycles # 1.735 GHz - 2,170,288,189 instructions # 1.60 insn per cycle - 0.783205677 seconds time elapsed + 1,357,390,482 cycles # 1.742 GHz + 2,169,212,126 instructions # 1.60 insn per cycle + 0.779795742 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4092) (512y: 32) (512z:79551) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.892981e-03 Avg ME (F77/C++) = 9.8929811982957326E-003 Relative difference = 2.0044082998332894e-08 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd0.txt index 30b5071b5..2e59aa225 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:28:07 +DATE: 2024-09-15_11:25:23 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.671280e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.671774e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.671942e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.663841e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.664390e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.664590e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 2.179035 sec +TOTAL : 2.203630 sec INFO: No Floating Point Exceptions have been reported - 7,454,613,030 cycles # 2.972 GHz - 15,438,571,901 instructions # 2.07 insn per cycle - 2.564208911 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 1 + 7,260,397,959 cycles # 2.866 GHz + 15,031,707,879 instructions # 2.07 insn per cycle + 2.589013700 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.108972e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.109238e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.109268e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.107763e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.108067e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.108098e+04 ) sec^-1 MeanMatrixElemValue = ( 1.856249e-04 +- 8.329951e-05 ) GeV^-6 -TOTAL : 3.409316 sec +TOTAL : 3.442022 sec INFO: No Floating Point Exceptions have been reported - 11,057,666,610 cycles # 2.961 GHz - 25,976,156,930 instructions # 2.35 insn per cycle - 3.792664161 seconds time elapsed + 10,932,120,354 cycles # 2.895 GHz + 24,906,946,249 instructions # 2.28 insn per cycle + 3.831975982 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.872263e-03 Avg ME (F77/GPU) = 9.8722599015656498E-003 Relative difference = 3.1385249252060663e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 7.690962e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.691161e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.691161e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.516129e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.516327e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.516327e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 6.867055 sec +TOTAL : 7.025685 sec INFO: No Floating Point Exceptions have been reported - 19,231,108,767 cycles # 2.799 GHz - 54,133,653,277 instructions # 2.81 insn per cycle - 6.871158287 seconds time elapsed + 19,256,305,943 cycles # 2.740 GHz + 54,130,622,749 instructions # 2.81 insn per cycle + 7.029878997 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:32000) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595861831675E-003 Relative difference = 3.457988134687711e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.564157e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.564257e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.564257e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.524890e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.524973e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.524973e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 3.376613 sec +TOTAL : 3.464849 sec INFO: No Floating Point Exceptions have been reported - 9,406,223,070 cycles # 2.783 GHz - 26,189,614,539 instructions # 2.78 insn per cycle - 3.380789677 seconds time elapsed + 9,453,784,509 cycles # 2.726 GHz + 26,186,103,091 instructions # 2.77 insn per cycle + 3.468732831 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:96049) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594844308162E-003 Relative difference = 3.5610570575237004e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.630251e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.630699e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.630699e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.508306e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.508754e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.508754e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.457110 sec +TOTAL : 1.507182 sec INFO: No Floating Point Exceptions have been reported - 4,072,790,882 cycles # 2.789 GHz - 9,249,316,005 instructions # 2.27 insn per cycle - 1.461211705 seconds time elapsed + 4,099,795,192 cycles # 2.715 GHz + 9,249,955,249 instructions # 2.26 insn per cycle + 1.510975685 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:84390) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.130909e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.131518e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.131518e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.116819e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.117442e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.117442e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.278845 sec +TOTAL : 1.284411 sec INFO: No Floating Point Exceptions have been reported - 3,501,587,241 cycles # 2.731 GHz - 8,183,389,621 instructions # 2.34 insn per cycle - 1.283034636 seconds time elapsed + 3,509,716,252 cycles # 2.725 GHz + 8,182,475,258 instructions # 2.33 insn per cycle + 1.288638878 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:80015) (512y: 79) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.612594e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.613211e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.613211e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.462021e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.462537e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.462537e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.463667 sec +TOTAL : 1.527279 sec INFO: No Floating Point Exceptions have been reported - 2,655,595,463 cycles # 1.810 GHz - 4,172,901,879 instructions # 1.57 insn per cycle - 1.467972309 seconds time elapsed + 2,661,319,941 cycles # 1.739 GHz + 4,172,569,565 instructions # 1.57 insn per cycle + 1.531717386 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2612) (512y: 93) (512z:78910) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 diff --git a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd1.txt index 55b2618d9..f2e4a2151 100644 --- a/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -21,44 +21,44 @@ make: Nothing to be done for 'all'. make: Nothing to be done for 'all'. -DATE: 2024-09-01_23:29:32 +DATE: 2024-09-15_11:26:49 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.668363e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.668845e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.669031e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.668216e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.668742e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.668891e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 2.178975 sec +TOTAL : 2.204926 sec INFO: No Floating Point Exceptions have been reported - 7,457,493,932 cycles # 2.978 GHz - 15,404,288,605 instructions # 2.07 insn per cycle - 2.560153423 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 1 + 7,354,907,186 cycles # 2.903 GHz + 15,835,326,846 instructions # 2.15 insn per cycle + 2.589353613 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.105339e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.105611e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.105641e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.111109e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.111413e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.111447e+04 ) sec^-1 MeanMatrixElemValue = ( 1.856249e-04 +- 8.329951e-05 ) GeV^-6 -TOTAL : 3.412909 sec +TOTAL : 3.435805 sec INFO: No Floating Point Exceptions have been reported - 11,131,620,298 cycles # 2.977 GHz - 26,091,817,296 instructions # 2.34 insn per cycle - 3.795284390 seconds time elapsed + 11,002,728,447 cycles # 2.923 GHz + 25,822,053,923 instructions # 2.35 insn per cycle + 3.822280777 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -66,33 +66,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 9.872263e-03 Avg ME (F77/GPU) = 9.8722599015656498E-003 Relative difference = 3.1385249252060663e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 7.937184e+01 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.937416e+01 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.937416e+01 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.824002e+01 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.824211e+01 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.824211e+01 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825549e-06 ) GeV^-6 -TOTAL : 6.645811 sec +TOTAL : 6.748238 sec INFO: No Floating Point Exceptions have been reported - 19,116,090,748 cycles # 2.875 GHz - 54,157,566,161 instructions # 2.83 insn per cycle - 6.649761760 seconds time elapsed + 19,286,477,225 cycles # 2.857 GHz + 54,157,907,603 instructions # 2.81 insn per cycle + 6.752432065 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:32202) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -100,31 +100,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722595861831675E-003 Relative difference = 3.457988134687711e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.593746e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.593833e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.593833e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.548001e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.548086e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.548086e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 3.315385 sec +TOTAL : 3.412561 sec INFO: No Floating Point Exceptions have been reported - 9,261,820,614 cycles # 2.791 GHz - 26,087,601,781 instructions # 2.82 insn per cycle - 3.319522422 seconds time elapsed + 9,302,368,855 cycles # 2.723 GHz + 26,085,336,117 instructions # 2.80 insn per cycle + 3.416771061 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:95938) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -132,31 +132,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594844308162E-003 Relative difference = 3.5610570575237004e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.574845e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.575287e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.575287e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.533570e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.534051e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.534051e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.477762 sec +TOTAL : 1.496264 sec INFO: No Floating Point Exceptions have been reported - 4,086,825,644 cycles # 2.759 GHz - 9,213,646,236 instructions # 2.25 insn per cycle - 1.481734504 seconds time elapsed + 4,086,923,304 cycles # 2.726 GHz + 9,212,952,806 instructions # 2.25 insn per cycle + 1.500090267 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:83864) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -164,31 +164,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.245121e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.245740e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.245740e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.068352e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.068931e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.068931e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.245877 sec +TOTAL : 1.299365 sec INFO: No Floating Point Exceptions have been reported - 3,507,145,990 cycles # 2.807 GHz - 8,168,649,004 instructions # 2.33 insn per cycle - 1.249959812 seconds time elapsed + 3,513,960,907 cycles # 2.698 GHz + 8,167,668,326 instructions # 2.32 insn per cycle + 1.303235401 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2:79421) (512y: 229) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -196,31 +196,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GG_TTXGGG_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.628651e+02 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.629248e+02 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.629248e+02 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.521239e+02 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.521794e+02 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.521794e+02 ) sec^-1 MeanMatrixElemValue = ( 1.187066e-05 +- 9.825548e-06 ) GeV^-6 -TOTAL : 1.460034 sec +TOTAL : 1.500932 sec INFO: No Floating Point Exceptions have been reported - 2,627,414,624 cycles # 1.795 GHz - 4,168,572,006 instructions # 1.59 insn per cycle - 1.464415967 seconds time elapsed + 2,617,549,535 cycles # 1.740 GHz + 4,166,941,618 instructions # 1.59 insn per cycle + 1.504880250 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1876) (512y: 175) (512z:78884) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 1240 channels { no-multichannel : 512 } @@ -228,8 +228,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 1240 channels { 1 : 32, 2 : 32, 4 : 32, 5 : 32, 7 : 32, 8 : 32, 14 : 32, 15 : 32, 16 : 32, 18 : 32, 19 : 32, 20 : 32, 22 : 32, 23 : 32, 24 : 32, 26 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gg_ttggg.mad/SubProcesses/P1_gg_ttxggg/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 9.872263e-03 Avg ME (F77/C++) = 9.8722594324461913E-003 Relative difference = 3.613714310412983e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0.txt index 752f3e4e2..73af5e5b3 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:21:53 +DATE: 2024-09-15_11:19:01 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.031687e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.003161e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.104462e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.740481e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.765338e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.886154e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.455310 sec +TOTAL : 0.459950 sec INFO: No Floating Point Exceptions have been reported - 1,914,069,990 cycles # 2.849 GHz - 2,713,664,499 instructions # 1.42 insn per cycle - 0.728378450 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,934,018,539 cycles # 2.861 GHz + 2,739,518,446 instructions # 1.42 insn per cycle + 0.734446139 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.192130e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.579973e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.785909e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.975676e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.474629e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.695966e+07 ) sec^-1 MeanMatrixElemValue = ( 2.602505e+02 +- 2.116328e+02 ) GeV^-2 -TOTAL : 0.533178 sec +TOTAL : 0.539678 sec INFO: No Floating Point Exceptions have been reported - 2,236,133,262 cycles # 2.909 GHz - 3,226,380,886 instructions # 1.44 insn per cycle - 0.827389063 seconds time elapsed + 2,257,806,163 cycles # 2.877 GHz + 3,239,125,642 instructions # 1.43 insn per cycle + 0.841027050 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424749e-01 Avg ME (F77/GPU) = 0.14247482467490466 Relative difference = 5.286902838873106e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.068548e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.091206e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.091206e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.056428e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.078475e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.078475e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 1.552747 sec +TOTAL : 1.570596 sec INFO: No Floating Point Exceptions have been reported - 4,620,087,308 cycles # 2.969 GHz - 13,191,209,906 instructions # 2.86 insn per cycle - 1.556877489 seconds time elapsed + 4,620,202,435 cycles # 2.935 GHz + 13,190,173,768 instructions # 2.85 insn per cycle + 1.574765138 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 707) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499481 Relative difference = 5.286896511435107e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.880560e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.951101e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.951101e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.870844e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.942105e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.942105e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.889978 sec +TOTAL : 0.895190 sec INFO: No Floating Point Exceptions have been reported - 2,637,556,758 cycles # 2.952 GHz - 7,554,793,042 instructions # 2.86 insn per cycle - 0.894227958 seconds time elapsed + 2,640,894,010 cycles # 2.940 GHz + 7,556,112,587 instructions # 2.86 insn per cycle + 0.899078617 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3099) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499475 Relative difference = 5.286896515331313e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.229284e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.441159e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.441159e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.155420e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.359383e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.359383e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.526334 sec +TOTAL : 0.539606 sec INFO: No Floating Point Exceptions have been reported - 1,488,988,294 cycles # 2.810 GHz - 3,159,434,723 instructions # 2.12 insn per cycle - 0.530437516 seconds time elapsed + 1,490,717,557 cycles # 2.746 GHz + 3,161,146,919 instructions # 2.12 insn per cycle + 0.543466540 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2991) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.574498e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.829667e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.829667e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.514709e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.763624e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.763624e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.477558 sec +TOTAL : 0.485581 sec INFO: No Floating Point Exceptions have been reported - 1,345,056,587 cycles # 2.796 GHz - 3,014,576,152 instructions # 2.24 insn per cycle - 0.481628256 seconds time elapsed + 1,345,992,067 cycles # 2.752 GHz + 3,013,895,719 instructions # 2.24 insn per cycle + 0.489750963 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2752) (512y: 104) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.397723e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.510771e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.510771e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.329309e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.438411e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.438411e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.704790 sec +TOTAL : 0.725847 sec INFO: No Floating Point Exceptions have been reported - 1,325,976,316 cycles # 1.872 GHz - 1,962,614,842 instructions # 1.48 insn per cycle - 0.709099149 seconds time elapsed + 1,326,647,346 cycles # 1.820 GHz + 1,963,906,161 instructions # 1.48 insn per cycle + 0.729744934 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1379) (512y: 106) (512z: 2218) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0_bridge.txt index e205a9649..87049bf6b 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:44:16 +DATE: 2024-09-15_11:47:47 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.345310e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.664571e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.664571e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.302816e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.642797e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.642797e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.479051 sec +TOTAL : 0.484911 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,024,905,494 cycles # 2.924 GHz - 3,010,761,757 instructions # 1.49 insn per cycle - 0.749424438 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 1,993,081,726 cycles # 2.857 GHz + 2,967,605,428 instructions # 1.49 insn per cycle + 0.755486323 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.221274e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.154965e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.154965e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.256871e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.326938e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.326938e+07 ) sec^-1 MeanMatrixElemValue = ( 2.602505e+02 +- 2.116328e+02 ) GeV^-2 -TOTAL : 0.753201 sec +TOTAL : 0.759153 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,928,569,908 cycles # 2.912 GHz - 4,501,106,831 instructions # 1.54 insn per cycle - 1.062426776 seconds time elapsed + 2,900,800,476 cycles # 2.878 GHz + 4,476,324,954 instructions # 1.54 insn per cycle + 1.066391830 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424749e-01 Avg ME (F77/GPU) = 0.14247482467490466 Relative difference = 5.286902838873106e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.079441e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.102836e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.102836e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.051618e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.074674e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.074674e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 1.542749 sec +TOTAL : 1.585397 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,649,053,239 cycles # 3.007 GHz - 13,196,358,277 instructions # 2.84 insn per cycle - 1.547064126 seconds time elapsed + 4,659,791,475 cycles # 2.933 GHz + 13,199,729,048 instructions # 2.83 insn per cycle + 1.589552076 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 707) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499481 Relative difference = 5.286896511435107e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.903842e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.977293e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.977293e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.863646e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.935223e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.935223e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.886250 sec +TOTAL : 0.905908 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,671,400,020 cycles # 3.001 GHz - 7,604,703,234 instructions # 2.85 insn per cycle - 0.890720613 seconds time elapsed + 2,672,075,267 cycles # 2.939 GHz + 7,605,973,490 instructions # 2.85 insn per cycle + 0.909977972 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3099) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499475 Relative difference = 5.286896515331313e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.228849e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.437424e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.437424e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.113398e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.317707e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.317707e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.532771 sec +TOTAL : 0.554094 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,514,010,227 cycles # 2.824 GHz - 3,208,515,118 instructions # 2.12 insn per cycle - 0.537156979 seconds time elapsed + 1,524,354,103 cycles # 2.734 GHz + 3,211,905,393 instructions # 2.11 insn per cycle + 0.558166519 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2991) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.428264e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.678035e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.678035e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.488860e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.737446e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.737446e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.505454 sec +TOTAL : 0.497012 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,390,457,987 cycles # 2.731 GHz - 3,065,685,884 instructions # 2.20 insn per cycle - 0.509808717 seconds time elapsed + 1,381,887,844 cycles # 2.761 GHz + 3,066,710,334 instructions # 2.22 insn per cycle + 0.501143809 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2752) (512y: 104) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.404789e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.521630e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.521630e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.170464e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.268423e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.268423e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.709220 sec +TOTAL : 0.785429 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,357,049,699 cycles # 1.904 GHz - 2,000,123,529 instructions # 1.47 insn per cycle - 0.713542278 seconds time elapsed + 1,369,203,746 cycles # 1.799 GHz + 2,005,266,999 instructions # 1.46 insn per cycle + 0.789533436 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1379) (512y: 106) (512z: 2218) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd1.txt index f94a52ab7..f184fc3b5 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:22:07 +DATE: 2024-09-15_11:19:15 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.978981e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.910532e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.009115e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.732857e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.764454e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.875095e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.453993 sec +TOTAL : 0.459022 sec INFO: No Floating Point Exceptions have been reported - 1,944,810,772 cycles # 2.908 GHz - 2,740,865,498 instructions # 1.41 insn per cycle - 0.726972885 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,935,515,541 cycles # 2.868 GHz + 2,740,568,582 instructions # 1.42 insn per cycle + 0.732282850 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.154104e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.465948e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.663513e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.938986e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.388894e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.605968e+07 ) sec^-1 MeanMatrixElemValue = ( 2.602505e+02 +- 2.116328e+02 ) GeV^-2 -TOTAL : 0.530243 sec +TOTAL : 0.543627 sec INFO: No Floating Point Exceptions have been reported - 2,242,321,005 cycles # 2.927 GHz - 3,256,187,861 instructions # 1.45 insn per cycle - 0.823764416 seconds time elapsed + 2,240,911,931 cycles # 2.849 GHz + 3,134,508,527 instructions # 1.40 insn per cycle + 0.843804985 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424749e-01 Avg ME (F77/GPU) = 0.14247482467490466 Relative difference = 5.286902838873106e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.081605e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.104353e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.104353e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.033389e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.055879e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.055879e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 1.533744 sec +TOTAL : 1.606028 sec INFO: No Floating Point Exceptions have been reported - 4,619,608,835 cycles # 3.005 GHz - 13,179,787,994 instructions # 2.85 insn per cycle - 1.537829933 seconds time elapsed + 4,632,143,331 cycles # 2.878 GHz + 13,180,119,009 instructions # 2.85 insn per cycle + 1.610268805 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 692) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499481 Relative difference = 5.286896511435107e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.883806e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.954980e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.954980e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.829571e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.900649e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.900649e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.888511 sec +TOTAL : 0.915734 sec INFO: No Floating Point Exceptions have been reported - 2,638,583,481 cycles # 2.959 GHz - 7,553,274,738 instructions # 2.86 insn per cycle - 0.892657592 seconds time elapsed + 2,643,771,941 cycles # 2.877 GHz + 7,554,150,292 instructions # 2.86 insn per cycle + 0.919868185 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3093) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467499475 Relative difference = 5.286896515331313e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.132913e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.333320e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.333320e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.046256e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.248866e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.248866e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.542044 sec +TOTAL : 0.558915 sec INFO: No Floating Point Exceptions have been reported - 1,493,314,483 cycles # 2.737 GHz - 3,158,681,228 instructions # 2.12 insn per cycle - 0.546207198 seconds time elapsed + 1,500,616,577 cycles # 2.669 GHz + 3,161,167,766 instructions # 2.11 insn per cycle + 0.563154837 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2976) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.575941e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.830718e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.830718e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.429175e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.674618e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.674618e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.477166 sec +TOTAL : 0.498371 sec INFO: No Floating Point Exceptions have been reported - 1,346,749,124 cycles # 2.802 GHz - 3,011,101,009 instructions # 2.24 insn per cycle - 0.481258455 seconds time elapsed + 1,352,614,614 cycles # 2.696 GHz + 3,013,058,203 instructions # 2.23 insn per cycle + 0.502370936 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2726) (512y: 104) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.401586e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.515098e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.515098e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.263352e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.370712e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.370712e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.703522 sec +TOTAL : 0.746831 sec INFO: No Floating Point Exceptions have been reported - 1,323,479,582 cycles # 1.872 GHz - 1,960,882,007 instructions # 1.48 insn per cycle - 0.707682489 seconds time elapsed + 1,330,812,654 cycles # 1.774 GHz + 1,962,138,478 instructions # 1.47 insn per cycle + 0.751010006 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1356) (512y: 106) (512z: 2218) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482467492589 Relative difference = 5.286901348574438e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0.txt index 539edfef0..9c9085f21 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:22:20 +DATE: 2024-09-15_11:19:29 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.045407e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.221377e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.365082e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.616183e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.859144e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.009356e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018174e+01 +- 1.429492e+01 ) GeV^-2 -TOTAL : 0.447666 sec +TOTAL : 0.455344 sec INFO: No Floating Point Exceptions have been reported - 1,945,143,368 cycles # 2.906 GHz - 2,736,215,762 instructions # 1.41 insn per cycle - 0.726464456 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,903,769,704 cycles # 2.832 GHz + 2,695,127,426 instructions # 1.42 insn per cycle + 0.728806465 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 169 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.771213e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.600955e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.919338e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.292895e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.269503e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.615665e+07 ) sec^-1 MeanMatrixElemValue = ( 2.571360e+02 +- 2.114020e+02 ) GeV^-2 -TOTAL : 0.485020 sec +TOTAL : 0.493521 sec INFO: No Floating Point Exceptions have been reported - 2,064,276,099 cycles # 2.909 GHz - 2,946,314,472 instructions # 1.43 insn per cycle - 0.768202354 seconds time elapsed + 2,090,898,444 cycles # 2.835 GHz + 2,942,471,441 instructions # 1.41 insn per cycle + 0.794240657 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424226e-01 Avg ME (F77/GPU) = 0.14247487904286338 Relative difference = 0.0003670698531228044 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.119951e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.145461e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.145461e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.085317e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.110333e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.110333e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 1.480791 sec +TOTAL : 1.528688 sec INFO: No Floating Point Exceptions have been reported - 4,405,520,694 cycles # 2.968 GHz - 12,951,927,506 instructions # 2.94 insn per cycle - 1.484750852 seconds time elapsed + 4,411,922,721 cycles # 2.879 GHz + 12,951,312,387 instructions # 2.94 insn per cycle + 1.532844163 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 645) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246861273719524 Relative difference = 8.940352641194861e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.931213e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.111077e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.111077e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.813599e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.988360e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.988360e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 0.575764 sec +TOTAL : 0.600071 sec INFO: No Floating Point Exceptions have been reported - 1,726,755,289 cycles # 2.983 GHz - 4,541,905,728 instructions # 2.63 insn per cycle - 0.579696563 seconds time elapsed + 1,729,759,970 cycles # 2.867 GHz + 4,541,750,353 instructions # 2.63 insn per cycle + 0.604044137 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3627) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246862329122401 Relative difference = 1.6348320966878032e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.741178e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.447926e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.447926e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.481903e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.160699e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.160699e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.302577 sec +TOTAL : 0.317183 sec INFO: No Floating Point Exceptions have been reported - 858,281,964 cycles # 2.805 GHz - 1,918,005,611 instructions # 2.23 insn per cycle - 0.306598837 seconds time elapsed + 858,921,512 cycles # 2.679 GHz + 1,917,766,555 instructions # 2.23 insn per cycle + 0.321171597 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3580) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.186652e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.004123e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.004123e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.857503e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.629025e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.629025e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.282428 sec +TOTAL : 0.298118 sec INFO: No Floating Point Exceptions have been reported - 802,950,150 cycles # 2.808 GHz - 1,834,564,140 instructions # 2.28 insn per cycle - 0.286463360 seconds time elapsed + 804,518,989 cycles # 2.670 GHz + 1,834,610,739 instructions # 2.28 insn per cycle + 0.301964643 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3402) (512y: 22) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.633415e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.094139e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.094139e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.365317e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.786659e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.786659e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018829e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.373155 sec +TOTAL : 0.395762 sec INFO: No Floating Point Exceptions have been reported - 727,080,964 cycles # 1.931 GHz - 1,308,398,620 instructions # 1.80 insn per cycle - 0.377057439 seconds time elapsed + 728,663,796 cycles # 1.826 GHz + 1,308,267,192 instructions # 1.80 insn per cycle + 0.399787635 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1963) (512y: 26) (512z: 2434) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491576758442 Relative difference = 1.1066920862943416e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0_bridge.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0_bridge.txt index 516b3c63c..f23dffbec 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0_bridge.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0_bridge.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,40 +11,40 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:44:29 +DATE: 2024-09-15_11:48:01 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 10 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -53,17 +53,17 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.036695e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.480472e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.480472e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.986387e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.435739e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.435739e+07 ) sec^-1 MeanMatrixElemValue = ( 2.017654e+01 +- 1.429183e+01 ) GeV^-2 -TOTAL : 0.460608 sec +TOTAL : 0.462861 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,967,208,517 cycles # 2.924 GHz - 2,913,604,143 instructions # 1.48 insn per cycle - 0.729608923 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge + 1,938,742,838 cycles # 2.865 GHz + 2,865,087,008 instructions # 1.48 insn per cycle + 0.732940290 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 --bridge WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost WARNING! Instantiate device Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks*gputhreads=16384) @@ -71,7 +71,7 @@ WARNING! Set grid in Bridge (nevt=16384, gpublocks=64, gputhreads=256, gpublocks ==PROF== Profiling "sigmaKin": launch__registers_per_thread 169 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 --bridge OMP= WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost WARNING! RamboHost selected: cannot use CurandDevice, will use CurandHost INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW @@ -80,18 +80,18 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.953788e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.785252e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.785252e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.036027e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.082450e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.082450e+07 ) sec^-1 MeanMatrixElemValue = ( 2.609941e+02 +- 2.115589e+02 ) GeV^-2 -TOTAL : 0.631447 sec +TOTAL : 0.632974 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 2,535,639,057 cycles # 2.933 GHz - 3,859,863,698 instructions # 1.52 insn per cycle - 0.922711155 seconds time elapsed + 2,495,936,905 cycles # 2.880 GHz + 3,785,157,902 instructions # 1.52 insn per cycle + 0.923834641 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -99,35 +99,35 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424226e-01 Avg ME (F77/GPU) = 0.14247487904286338 Relative difference = 0.0003670698531228044 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.129048e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.155080e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.155080e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.104272e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.129547e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.129547e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 1.471706 sec +TOTAL : 1.505088 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 4,420,739,520 cycles # 2.997 GHz - 12,956,497,906 instructions # 2.93 insn per cycle - 1.475936292 seconds time elapsed + 4,422,322,267 cycles # 2.932 GHz + 12,955,751,055 instructions # 2.93 insn per cycle + 1.509164533 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 645) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -135,33 +135,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246861273719524 Relative difference = 8.940352641194861e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.945017e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.127579e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.127579e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.849156e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.028095e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.028095e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 0.577519 sec +TOTAL : 0.596878 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 1,746,510,912 cycles # 3.006 GHz - 4,590,294,549 instructions # 2.63 insn per cycle - 0.581528587 seconds time elapsed + 1,746,639,368 cycles # 2.911 GHz + 4,590,056,426 instructions # 2.63 insn per cycle + 0.600772729 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3627) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -169,33 +169,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246862329122401 Relative difference = 1.6348320966878032e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.790714e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.493578e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.493578e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.482456e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.156915e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.156915e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.304247 sec +TOTAL : 0.321160 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 875,834,497 cycles # 2.846 GHz - 1,955,180,350 instructions # 2.23 insn per cycle - 0.308403282 seconds time elapsed + 875,522,703 cycles # 2.698 GHz + 1,954,476,479 instructions # 2.23 insn per cycle + 0.325091323 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3580) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -203,33 +203,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.189465e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.016700e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.016700e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.960780e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.751467e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.751467e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.286303 sec +TOTAL : 0.296758 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 822,678,068 cycles # 2.838 GHz - 1,871,812,412 instructions # 2.28 insn per cycle - 0.290432615 seconds time elapsed + 821,090,022 cycles # 2.738 GHz + 1,871,468,752 instructions # 2.28 insn per cycle + 0.300472695 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3402) (512y: 22) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -237,33 +237,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe -p 64 256 10 --bridge OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW WARNING! Instantiate host Bridge (nevt=16384) Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.670499e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.135311e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.135311e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.492830e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.932362e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.932362e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018829e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.374584 sec +TOTAL : 0.388889 sec INFO: No Floating Point Exceptions have been reported INFO: No Floating Point Exceptions have been reported - 749,472,169 cycles # 1.981 GHz - 1,349,919,039 instructions # 1.80 insn per cycle - 0.378841460 seconds time elapsed + 746,594,357 cycles # 1.904 GHz + 1,349,630,324 instructions # 1.81 insn per cycle + 0.392744433 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1963) (512y: 26) (512z: 2434) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -271,8 +271,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491576758442 Relative difference = 1.1066920862943416e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd1.txt index 5c7c3206a..e2521e45b 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:22:32 +DATE: 2024-09-15_11:19:41 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.996806e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.140865e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.289001e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.639867e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.865475e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.015127e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018174e+01 +- 1.429492e+01 ) GeV^-2 -TOTAL : 0.447667 sec +TOTAL : 0.454979 sec INFO: No Floating Point Exceptions have been reported - 1,939,854,779 cycles # 2.902 GHz - 2,753,564,074 instructions # 1.42 insn per cycle - 0.725490660 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,901,448,560 cycles # 2.824 GHz + 2,678,183,164 instructions # 1.41 insn per cycle + 0.730072764 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 169 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 5.820533e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.706896e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.005515e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.246644e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.993104e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.325490e+07 ) sec^-1 MeanMatrixElemValue = ( 2.571360e+02 +- 2.114020e+02 ) GeV^-2 -TOTAL : 0.482853 sec +TOTAL : 0.496812 sec INFO: No Floating Point Exceptions have been reported - 2,066,417,058 cycles # 2.916 GHz - 2,981,752,243 instructions # 1.44 insn per cycle - 0.766268306 seconds time elapsed + 2,083,867,357 cycles # 2.832 GHz + 2,934,470,565 instructions # 1.41 insn per cycle + 0.792648211 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424226e-01 Avg ME (F77/GPU) = 0.14247487904286338 Relative difference = 0.0003670698531228044 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.131393e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.156981e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.156981e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.078136e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.103342e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.103342e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 1.465329 sec +TOTAL : 1.538413 sec INFO: No Floating Point Exceptions have been reported - 4,403,508,539 cycles # 2.998 GHz - 12,927,457,946 instructions # 2.94 insn per cycle - 1.469265049 seconds time elapsed + 4,411,092,348 cycles # 2.861 GHz + 12,926,836,759 instructions # 2.93 insn per cycle + 1.542610115 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 630) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246861273719524 Relative difference = 8.940352641194861e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.923741e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.107237e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.107237e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.816554e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.994652e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.994652e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018564e+01 +- 1.429903e+01 ) GeV^-2 -TOTAL : 0.577117 sec +TOTAL : 0.599654 sec INFO: No Floating Point Exceptions have been reported - 1,726,421,109 cycles # 2.975 GHz - 4,536,755,110 instructions # 2.63 insn per cycle - 0.581051834 seconds time elapsed + 1,728,903,265 cycles # 2.870 GHz + 4,536,279,042 instructions # 2.62 insn per cycle + 0.603646034 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3611) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424686e-01 Avg ME (F77/C++) = 0.14246862329122401 Relative difference = 1.6348320966878032e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.757866e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.468995e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.468995e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.299874e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.938357e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.938357e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.301649 sec +TOTAL : 0.327791 sec INFO: No Floating Point Exceptions have been reported - 856,537,413 cycles # 2.808 GHz - 1,914,811,873 instructions # 2.24 insn per cycle - 0.305509856 seconds time elapsed + 861,849,665 cycles # 2.602 GHz + 1,914,633,101 instructions # 2.22 insn per cycle + 0.331876637 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3550) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.174332e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.002332e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.002332e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.927651e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.715679e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.715679e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018828e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.282627 sec +TOTAL : 0.294357 sec INFO: No Floating Point Exceptions have been reported - 801,753,582 cycles # 2.803 GHz - 1,830,571,668 instructions # 2.28 insn per cycle - 0.286587480 seconds time elapsed + 802,533,600 cycles # 2.696 GHz + 1,830,391,280 instructions # 2.28 insn per cycle + 0.298329557 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3366) (512y: 22) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491543012991 Relative difference = 1.0830068962165901e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.655287e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.123588e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.123588e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.433633e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.866083e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.866083e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018829e+01 +- 1.429922e+01 ) GeV^-2 -TOTAL : 0.371375 sec +TOTAL : 0.389558 sec INFO: No Floating Point Exceptions have been reported - 728,666,338 cycles # 1.944 GHz - 1,306,341,029 instructions # 1.79 insn per cycle - 0.375409232 seconds time elapsed + 729,078,705 cycles # 1.856 GHz + 1,305,984,013 instructions # 1.79 insn per cycle + 0.393475655 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1926) (512y: 26) (512z: 2437) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247491576758442 Relative difference = 1.1066920862943416e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd0.txt index e2c10d4bc..75ffaff93 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:22:44 +DATE: 2024-09-15_11:19:53 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.042271e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.019347e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.126926e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.751782e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.854275e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.972003e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.455575 sec +TOTAL : 0.462457 sec INFO: No Floating Point Exceptions have been reported - 1,949,957,691 cycles # 2.915 GHz - 2,774,209,464 instructions # 1.42 insn per cycle - 0.728034530 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 + 1,917,992,386 cycles # 2.823 GHz + 2,716,857,811 instructions # 1.42 insn per cycle + 0.737791701 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.182186e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.548184e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.751701e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.933049e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.480174e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.706062e+07 ) sec^-1 MeanMatrixElemValue = ( 2.602505e+02 +- 2.116328e+02 ) GeV^-2 -TOTAL : 0.531018 sec +TOTAL : 0.542910 sec INFO: No Floating Point Exceptions have been reported - 2,238,994,244 cycles # 2.915 GHz - 3,265,794,068 instructions # 1.46 insn per cycle - 0.824796035 seconds time elapsed + 2,260,071,894 cycles # 2.877 GHz + 3,201,078,521 instructions # 1.42 insn per cycle + 0.842582370 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424749e-01 Avg ME (F77/GPU) = 0.14247482577104625 Relative difference = 5.209967070245855e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.070148e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.092369e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.092369e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.028418e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.050644e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.050644e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 1.549834 sec +TOTAL : 1.613813 sec INFO: No Floating Point Exceptions have been reported - 4,636,067,594 cycles # 2.985 GHz - 13,177,808,559 instructions # 2.84 insn per cycle - 1.553904132 seconds time elapsed + 4,647,383,877 cycles # 2.879 GHz + 13,178,063,049 instructions # 2.84 insn per cycle + 1.618051260 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 681) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482734618697 Relative difference = 5.099411406595165e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.851566e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.920581e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.920581e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.864504e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.934483e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.934483e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.903963 sec +TOTAL : 0.898369 sec INFO: No Floating Point Exceptions have been reported - 2,648,666,014 cycles # 2.920 GHz - 7,474,201,263 instructions # 2.82 insn per cycle - 0.908149777 seconds time elapsed + 2,648,200,185 cycles # 2.937 GHz + 7,475,755,342 instructions # 2.82 insn per cycle + 0.902206814 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3153) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482734618697 Relative difference = 5.099411406595165e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.980538e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.167049e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.167049e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.200611e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.408501e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.408501e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.569921 sec +TOTAL : 0.532171 sec INFO: No Floating Point Exceptions have been reported - 1,470,951,187 cycles # 2.564 GHz - 3,127,090,607 instructions # 2.13 insn per cycle - 0.574168476 seconds time elapsed + 1,476,374,652 cycles # 2.757 GHz + 3,128,702,616 instructions # 2.12 insn per cycle + 0.536024340 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3131) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.682566e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.954257e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.954257e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.587903e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.854303e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.854303e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.463686 sec +TOTAL : 0.476990 sec INFO: No Floating Point Exceptions have been reported - 1,321,491,982 cycles # 2.828 GHz - 2,981,266,637 instructions # 2.26 insn per cycle - 0.467810621 seconds time elapsed + 1,322,669,287 cycles # 2.754 GHz + 2,982,885,294 instructions # 2.26 insn per cycle + 0.480825528 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2893) (512y: 110) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.347586e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.455232e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.455232e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.251912e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.353383e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.353383e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.719457 sec +TOTAL : 0.750102 sec INFO: No Floating Point Exceptions have been reported - 1,362,323,271 cycles # 1.885 GHz - 1,990,651,022 instructions # 1.46 insn per cycle - 0.723612725 seconds time elapsed + 1,363,693,421 cycles # 1.811 GHz + 1,991,339,845 instructions # 1.46 insn per cycle + 0.753947194 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1679) (512y: 108) (512z: 2252) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 diff --git a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd1.txt index 731b43e37..40582e53f 100644 --- a/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux' -DATE: 2024-09-01_23:22:58 +DATE: 2024-09-15_11:20:07 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.998475e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.914130e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.011656e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.750483e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.807638e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.927006e+07 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.450635 sec +TOTAL : 0.460124 sec INFO: No Floating Point Exceptions have been reported - 1,944,746,281 cycles # 2.916 GHz - 2,764,543,101 instructions # 1.42 insn per cycle - 0.724024546 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 + 1,938,834,678 cycles # 2.862 GHz + 2,712,058,421 instructions # 1.40 insn per cycle + 0.735469517 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 3.154229e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.471183e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.669362e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.925117e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.366077e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.584033e+07 ) sec^-1 MeanMatrixElemValue = ( 2.602505e+02 +- 2.116328e+02 ) GeV^-2 -TOTAL : 0.532845 sec +TOTAL : 0.544645 sec INFO: No Floating Point Exceptions have been reported - 2,225,872,015 cycles # 2.895 GHz - 3,236,460,250 instructions # 1.45 insn per cycle - 0.825344230 seconds time elapsed + 2,249,855,314 cycles # 2.863 GHz + 3,222,814,057 instructions # 1.43 insn per cycle + 0.844200129 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.424749e-01 Avg ME (F77/GPU) = 0.14247482577104625 Relative difference = 5.209967070245855e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.075863e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.098691e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.098691e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.054095e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.076295e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.076295e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 1.541791 sec +TOTAL : 1.574055 sec INFO: No Floating Point Exceptions have been reported - 4,642,155,557 cycles # 3.005 GHz - 13,166,673,520 instructions # 2.84 insn per cycle - 1.545817949 seconds time elapsed + 4,641,890,435 cycles # 2.943 GHz + 13,165,898,661 instructions # 2.84 insn per cycle + 1.578249512 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 666) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482734618697 Relative difference = 5.099411406595165e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.900859e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.971794e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.971794e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.867370e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.936884e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.936884e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.880251 sec +TOTAL : 0.896912 sec INFO: No Floating Point Exceptions have been reported - 2,634,622,015 cycles # 2.982 GHz - 7,476,028,207 instructions # 2.84 insn per cycle - 0.884332319 seconds time elapsed + 2,636,737,245 cycles # 2.930 GHz + 7,477,755,477 instructions # 2.84 insn per cycle + 0.900719288 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3142) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482734618697 Relative difference = 5.099411406595165e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.279907e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.491191e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.491191e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.202775e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.410191e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.410191e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.518217 sec +TOTAL : 0.531412 sec INFO: No Floating Point Exceptions have been reported - 1,466,678,966 cycles # 2.811 GHz - 3,127,758,508 instructions # 2.13 insn per cycle - 0.522369566 seconds time elapsed + 1,468,072,782 cycles # 2.747 GHz + 3,129,202,339 instructions # 2.13 insn per cycle + 0.535248151 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3109) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.666233e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.933754e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.933754e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.576512e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.841608e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.841608e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.465925 sec +TOTAL : 0.477966 sec INFO: No Floating Point Exceptions have been reported - 1,319,548,349 cycles # 2.812 GHz - 2,981,592,473 instructions # 2.26 insn per cycle - 0.470005601 seconds time elapsed + 1,324,577,804 cycles # 2.753 GHz + 2,983,698,636 instructions # 2.25 insn per cycle + 0.481692847 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2869) (512y: 110) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/check_cpp.exe -p 64 256 10 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SM_GUX_TTXUX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.352608e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.463501e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.463501e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.229034e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.331255e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.331255e+05 ) sec^-1 MeanMatrixElemValue = ( 2.018083e+01 +- 1.429474e+01 ) GeV^-2 -TOTAL : 0.717564 sec +TOTAL : 0.757523 sec INFO: No Floating Point Exceptions have been reported - 1,362,472,140 cycles # 1.890 GHz - 1,989,923,600 instructions # 1.46 insn per cycle - 0.721628842 seconds time elapsed + 1,366,953,688 cycles # 1.797 GHz + 1,991,556,146 instructions # 1.46 insn per cycle + 0.761326972 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1655) (512y: 108) (512z: 2252) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 5 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 5 channels { 1 : 128, 2 : 96, 3 : 96, 4 : 96, 5 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/gq_ttq.mad/SubProcesses/P1_gux_ttxux/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.424749e-01 Avg ME (F77/C++) = 0.14247482643254802 Relative difference = 5.163537715318965e-07 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd0.txt index 85c78141b..a10430f20 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:03:25 +DATE: 2024-09-15_12:19:52 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.564691e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.007021e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.548726e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.222962e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.849418e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.427313e+07 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 0.522287 sec +TOTAL : 0.531972 sec INFO: No Floating Point Exceptions have been reported - 2,186,415,358 cycles # 2.898 GHz - 3,130,135,893 instructions # 1.43 insn per cycle - 0.811473600 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,207,295,929 cycles # 2.875 GHz + 3,148,652,719 instructions # 1.43 insn per cycle + 0.824191400 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 228 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313472e+00 Avg ME (F77/GPU) = 4.3134710926110280 Relative difference = 2.1036162329561614e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.649154e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.686776e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.686776e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.605446e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.642912e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.642912e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 6.466778 sec +TOTAL : 6.682964 sec INFO: No Floating Point Exceptions have been reported - 19,279,079,475 cycles # 2.980 GHz - 51,925,969,991 instructions # 2.69 insn per cycle - 6.471928509 seconds time elapsed + 19,598,347,374 cycles # 2.930 GHz + 52,065,080,941 instructions # 2.66 insn per cycle + 6.694844262 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 668) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926105795 Relative difference = 2.1036172727915933e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.980039e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.114590e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.114590e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.916629e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.051442e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.051442e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.625823 sec +TOTAL : 3.747547 sec INFO: No Floating Point Exceptions have been reported - 10,900,387,506 cycles # 3.003 GHz - 30,787,661,791 instructions # 2.82 insn per cycle - 3.631002102 seconds time elapsed + 11,065,354,139 cycles # 2.943 GHz + 30,912,254,749 instructions # 2.79 insn per cycle + 3.760361851 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2914) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926105795 Relative difference = 2.1036172727915933e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.809628e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.159488e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.159488e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.668387e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.008748e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.008748e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.287459 sec +TOTAL : 2.399916 sec INFO: No Floating Point Exceptions have been reported - 6,475,661,061 cycles # 2.826 GHz - 13,666,695,330 instructions # 2.11 insn per cycle - 2.292637909 seconds time elapsed + 6,627,221,489 cycles # 2.749 GHz + 13,792,796,598 instructions # 2.08 insn per cycle + 2.412653295 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2941) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.229667e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.640727e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.640727e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.129922e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.540308e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.540308e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.112314 sec +TOTAL : 2.198225 sec INFO: No Floating Point Exceptions have been reported - 5,956,175,949 cycles # 2.814 GHz - 13,009,022,456 instructions # 2.18 insn per cycle - 2.117497927 seconds time elapsed + 6,104,431,058 cycles # 2.762 GHz + 13,134,794,290 instructions # 2.15 insn per cycle + 2.210920696 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2667) (512y: 146) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.552529e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.739990e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.739990e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.449384e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.629220e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.629220e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.059875 sec +TOTAL : 3.193674 sec INFO: No Floating Point Exceptions have been reported - 5,839,726,481 cycles # 1.906 GHz - 8,588,748,930 instructions # 1.47 insn per cycle - 3.065145740 seconds time elapsed + 5,993,463,965 cycles # 1.870 GHz + 8,712,960,993 instructions # 1.45 insn per cycle + 3.206184057 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1506) (512y: 128) (512z: 1943) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd1.txt index 0af02463f..01ceafd1d 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:03:51 +DATE: 2024-09-15_12:20:19 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.554397e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.959544e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.498828e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.181438e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.797209e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.367517e+07 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 0.520674 sec +TOTAL : 0.531302 sec INFO: No Floating Point Exceptions have been reported - 2,207,639,246 cycles # 2.933 GHz - 3,209,912,765 instructions # 1.45 insn per cycle - 0.809508240 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,216,417,295 cycles # 2.883 GHz + 3,137,968,070 instructions # 1.42 insn per cycle + 0.825226040 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 216 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313472e+00 Avg ME (F77/GPU) = 4.3134710926110280 Relative difference = 2.1036162329561614e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.736140e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.778559e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.778559e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.706608e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.748828e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.748828e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 6.148636 sec +TOTAL : 6.299466 sec INFO: No Floating Point Exceptions have been reported - 18,371,910,047 cycles # 2.986 GHz - 50,052,942,467 instructions # 2.72 insn per cycle - 6.153834062 seconds time elapsed + 18,540,883,021 cycles # 2.938 GHz + 50,178,474,604 instructions # 2.71 insn per cycle + 6.311951743 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 626) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926105795 Relative difference = 2.1036172727915933e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.139479e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.287984e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.287984e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.062664e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.211274e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.211274e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.448725 sec +TOTAL : 3.576786 sec INFO: No Floating Point Exceptions have been reported - 10,387,878,283 cycles # 3.008 GHz - 29,165,847,979 instructions # 2.81 insn per cycle - 3.454003397 seconds time elapsed + 10,549,321,378 cycles # 2.940 GHz + 29,289,408,214 instructions # 2.78 insn per cycle + 3.589213709 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2732) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926105795 Relative difference = 2.1036172727915933e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.453814e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.754112e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.754112e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.340015e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.632096e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.632096e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.462610 sec +TOTAL : 2.568858 sec INFO: No Floating Point Exceptions have been reported - 6,945,615,681 cycles # 2.815 GHz - 15,149,897,484 instructions # 2.18 insn per cycle - 2.468064425 seconds time elapsed + 7,118,801,409 cycles # 2.759 GHz + 15,276,261,936 instructions # 2.15 insn per cycle + 2.581007821 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3021) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.615593e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.939602e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.939602e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.507726e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.822175e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.822175e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.378771 sec +TOTAL : 2.479110 sec INFO: No Floating Point Exceptions have been reported - 6,687,743,595 cycles # 2.806 GHz - 14,621,758,561 instructions # 2.19 insn per cycle - 2.383962834 seconds time elapsed + 6,890,334,799 cycles # 2.767 GHz + 14,747,969,860 instructions # 2.14 insn per cycle + 2.491499387 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2617) (512y: 302) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.435627e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.606278e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.606278e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.315391e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.482899e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.482899e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.160533 sec +TOTAL : 3.316209 sec INFO: No Floating Point Exceptions have been reported - 6,041,475,634 cycles # 1.909 GHz - 10,338,847,329 instructions # 1.71 insn per cycle - 3.165865752 seconds time elapsed + 6,207,380,257 cycles # 1.865 GHz + 10,464,609,822 instructions # 1.69 insn per cycle + 3.328585456 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1268) (512y: 214) (512z: 2130) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313472e+00 Avg ME (F77/C++) = 4.3134710926107935 Relative difference = 2.103616776553298e-07 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt index 5fcaa607c..2ef1c54aa 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:04:17 +DATE: 2024-09-15_12:20:46 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.404305e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.566258e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.650776e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.552559e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.511007e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.603394e+08 ) sec^-1 MeanMatrixElemValue = ( 7.154219e+00 +- 1.620281e-01 ) GeV^0 -TOTAL : 0.484135 sec +TOTAL : 0.491259 sec INFO: No Floating Point Exceptions have been reported - 2,071,305,552 cycles # 2.928 GHz - 2,975,599,567 instructions # 1.44 insn per cycle - 0.765951641 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,068,896,846 cycles # 2.881 GHz + 2,979,901,367 instructions # 1.44 insn per cycle + 0.776426531 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 131 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313490e+00 Avg ME (F77/GPU) = 4.3136695491848513 Relative difference = 4.162503792787837e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.706014e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.748099e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.748099e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.683914e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.725672e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.725672e+05 ) sec^-1 MeanMatrixElemValue = ( 7.175644e+00 +- 1.658767e-01 ) GeV^0 -TOTAL : 6.232162 sec +TOTAL : 6.333148 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 18,618,405,428 cycles # 2.986 GHz - 51,216,623,324 instructions # 2.75 insn per cycle - 6.237206550 seconds time elapsed + 18,682,476,989 cycles # 2.947 GHz + 51,267,470,348 instructions # 2.74 insn per cycle + 6.341547157 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 625) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,8 +104,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313574e+00 @@ -113,24 +113,24 @@ Avg ME (F77/C++) = 4.3135738277342170 Relative difference = 3.9935743068669333e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.053495e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.316601e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.316601e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.015012e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.280109e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.280109e+05 ) sec^-1 MeanMatrixElemValue = ( 7.175642e+00 +- 1.658767e-01 ) GeV^0 -TOTAL : 2.671825 sec +TOTAL : 2.718050 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 7,933,798,435 cycles # 2.965 GHz - 19,318,604,169 instructions # 2.43 insn per cycle - 2.676827002 seconds time elapsed + 8,007,664,837 cycles # 2.940 GHz + 19,370,996,217 instructions # 2.42 insn per cycle + 2.726376718 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3542) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -138,8 +138,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313572e+00 @@ -147,24 +147,24 @@ Avg ME (F77/C++) = 4.3135722697479650 Relative difference = 6.253470796314402e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.022508e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.040916e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.040916e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.789023e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.799247e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.799247e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 1.391682 sec +TOTAL : 1.452394 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 3,945,769,791 cycles # 2.827 GHz - 8,833,631,799 instructions # 2.24 insn per cycle - 1.396789340 seconds time elapsed + 4,027,415,196 cycles # 2.759 GHz + 8,886,566,152 instructions # 2.21 insn per cycle + 1.460503609 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3715) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -172,31 +172,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313565e+00 Avg ME (F77/C++) = 4.3135645242873579 Relative difference = 1.1028294269894893e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.559238e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.732061e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.732061e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.322323e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.475598e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.475598e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 1.310268 sec +TOTAL : 1.366660 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 3,728,688,019 cycles # 2.837 GHz - 8,435,564,346 instructions # 2.26 insn per cycle - 1.315273778 seconds time elapsed + 3,807,036,059 cycles # 2.770 GHz + 8,489,981,547 instructions # 2.23 insn per cycle + 1.374788749 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3543) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -204,31 +204,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 4.313565e+00 Avg ME (F77/C++) = 4.3135645242873579 Relative difference = 1.1028294269894893e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.151674e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.721217e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.721217e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.974329e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.534282e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.534282e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 1.790416 sec +TOTAL : 1.862736 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 3,506,346,207 cycles # 1.954 GHz - 6,244,372,214 instructions # 1.78 insn per cycle - 1.795521362 seconds time elapsed + 3,570,392,990 cycles # 1.910 GHz + 6,298,404,091 instructions # 1.76 insn per cycle + 1.870756064 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2323) (512y: 24) (512z: 2290) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -236,8 +236,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313564e+00 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd1.txt index f789a36ed..479ebdb20 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:04:39 +DATE: 2024-09-15_12:21:08 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.689698e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.669285e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.767200e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.776065e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.594605e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.702542e+08 ) sec^-1 MeanMatrixElemValue = ( 7.154219e+00 +- 1.620281e-01 ) GeV^0 -TOTAL : 0.483733 sec +TOTAL : 0.491621 sec INFO: No Floating Point Exceptions have been reported - 2,063,650,160 cycles # 2.921 GHz - 2,954,472,232 instructions # 1.43 insn per cycle - 0.765340835 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,069,264,305 cycles # 2.877 GHz + 2,928,235,838 instructions # 1.42 insn per cycle + 0.775773692 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 125 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313490e+00 Avg ME (F77/GPU) = 4.3136695491848513 Relative difference = 4.162503792787837e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.766379e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.810796e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.810796e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.731608e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.775696e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.775696e+05 ) sec^-1 MeanMatrixElemValue = ( 7.175644e+00 +- 1.658767e-01 ) GeV^0 -TOTAL : 6.020230 sec +TOTAL : 6.161667 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 18,028,435,551 cycles # 2.993 GHz - 49,601,886,319 instructions # 2.75 insn per cycle - 6.025158583 seconds time elapsed + 18,113,353,892 cycles # 2.937 GHz + 49,656,566,510 instructions # 2.74 insn per cycle + 6.170127822 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 613) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,8 +104,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313574e+00 @@ -113,24 +113,24 @@ Avg ME (F77/C++) = 4.3135738277342170 Relative difference = 3.9935743068669333e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.615170e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.957825e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.957825e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.528214e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.868162e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.868162e+05 ) sec^-1 MeanMatrixElemValue = ( 7.175642e+00 +- 1.658767e-01 ) GeV^0 -TOTAL : 2.356923 sec +TOTAL : 2.421156 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 7,098,118,019 cycles # 3.006 GHz - 18,485,349,164 instructions # 2.60 insn per cycle - 2.362156827 seconds time elapsed + 7,159,836,216 cycles # 2.949 GHz + 18,538,672,579 instructions # 2.59 insn per cycle + 2.429136947 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3234) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -138,8 +138,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313572e+00 @@ -147,24 +147,24 @@ Avg ME (F77/C++) = 4.3135722697479650 Relative difference = 6.253470796314402e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.522988e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.985731e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.985731e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.353305e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.808520e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.808520e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 1.981973 sec +TOTAL : 2.063917 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 5,629,917,490 cycles # 2.834 GHz - 10,848,645,741 instructions # 1.93 insn per cycle - 1.986923799 seconds time elapsed + 5,718,285,058 cycles # 2.760 GHz + 10,903,070,951 instructions # 1.91 insn per cycle + 2.072527320 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4274) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -172,8 +172,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313565e+00 @@ -181,24 +181,24 @@ Avg ME (F77/C++) = 4.3135645242873579 Relative difference = 1.1028294269894893e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.583363e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.053605e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.053605e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.452070e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.924355e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.924355e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 1.963258 sec +TOTAL : 2.029021 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 5,552,996,034 cycles # 2.822 GHz - 10,546,245,088 instructions # 1.90 insn per cycle - 1.968423168 seconds time elapsed + 5,634,694,028 cycles # 2.767 GHz + 10,598,235,094 instructions # 1.88 insn per cycle + 2.037144953 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 4135) (512y: 12) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -206,8 +206,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313565e+00 @@ -215,24 +215,24 @@ Avg ME (F77/C++) = 4.3135645242873579 Relative difference = 1.1028294269894893e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.527750e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.831624e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.831624e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.351507e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.637189e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.637189e+05 ) sec^-1 MeanMatrixElemValue = ( 7.198861e+00 +- 1.710281e-01 ) GeV^0 -TOTAL : 2.402533 sec +TOTAL : 2.516038 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 4,632,613,207 cycles # 1.926 GHz - 8,660,145,416 instructions # 1.87 insn per cycle - 2.407440167 seconds time elapsed + 4,700,188,022 cycles # 1.863 GHz + 8,712,811,590 instructions # 1.85 insn per cycle + 2.524039667 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2799) (512y: 0) (512z: 2885) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -240,8 +240,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313564e+00 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd0.txt index f9d2dff64..7f1052231 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:05:01 +DATE: 2024-09-15_12:21:31 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.542911e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.940059e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.486530e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.233444e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.828530e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.380985e+07 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 0.526869 sec +TOTAL : 0.531166 sec INFO: No Floating Point Exceptions have been reported - 2,202,869,848 cycles # 2.914 GHz - 3,187,431,708 instructions # 1.45 insn per cycle - 0.815017923 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,204,089,924 cycles # 2.871 GHz + 3,157,003,197 instructions # 1.43 insn per cycle + 0.824717149 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 228 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313472e+00 Avg ME (F77/GPU) = 4.3134711012809239 Relative difference = 2.0835166567625394e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.556009e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.589038e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.589038e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.513438e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.546541e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.546541e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 6.847582 sec +TOTAL : 7.083035 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 20,531,344,425 cycles # 2.996 GHz - 51,924,253,983 instructions # 2.53 insn per cycle - 6.852906835 seconds time elapsed + 20,836,157,287 cycles # 2.937 GHz + 52,059,859,689 instructions # 2.50 insn per cycle + 7.095325403 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 655) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,8 +104,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -113,24 +113,24 @@ Avg ME (F77/C++) = 4.3134711778082178 Relative difference = 1.906102050071626e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.816147e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.936755e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.936755e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.708543e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.825114e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.825114e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.830973 sec +TOTAL : 4.025851 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 11,500,473,942 cycles # 2.998 GHz - 30,593,646,107 instructions # 2.66 insn per cycle - 3.836311415 seconds time elapsed + 11,676,241,949 cycles # 2.892 GHz + 30,719,909,890 instructions # 2.63 insn per cycle + 4.038601753 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2971) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -138,8 +138,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -147,24 +147,24 @@ Avg ME (F77/C++) = 4.3134711778082178 Relative difference = 1.906102050071626e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.569633e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.880415e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.880415e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.506319e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.824086e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.824086e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.402556 sec +TOTAL : 2.479724 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 6,695,614,069 cycles # 2.782 GHz - 13,609,071,038 instructions # 2.03 insn per cycle - 2.407778282 seconds time elapsed + 6,856,020,570 cycles # 2.752 GHz + 13,733,686,621 instructions # 2.00 insn per cycle + 2.492002268 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3118) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -172,8 +172,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -181,24 +181,24 @@ Avg ME (F77/C++) = 4.3134712319139954 Relative difference = 1.7806676491157786e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.065722e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.449896e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.449896e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.929662e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.305854e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.305854e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.178378 sec +TOTAL : 2.278940 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 6,166,178,947 cycles # 2.825 GHz - 12,973,644,724 instructions # 2.10 insn per cycle - 2.183709011 seconds time elapsed + 6,324,440,516 cycles # 2.761 GHz + 13,099,663,654 instructions # 2.07 insn per cycle + 2.291244442 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2851) (512y: 150) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -206,8 +206,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -215,24 +215,24 @@ Avg ME (F77/C++) = 4.3134712319139954 Relative difference = 1.7806676491157786e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.224497e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.375730e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.375730e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.121063e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.267193e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.267193e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.361722 sec +TOTAL : 3.513123 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 6,395,645,824 cycles # 1.900 GHz - 8,700,671,655 instructions # 1.36 insn per cycle - 3.366960874 seconds time elapsed + 6,549,229,378 cycles # 1.858 GHz + 8,826,958,587 instructions # 1.35 insn per cycle + 3.525479379 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1792) (512y: 130) (512z: 2013) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -240,8 +240,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 diff --git a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd1.txt index 6c2855449..b5ff528c4 100644 --- a/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx' -DATE: 2024-09-02_00:05:28 +DATE: 2024-09-15_12:21:59 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.541786e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.916256e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.462995e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.263927e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.696044e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.276288e+07 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 0.525979 sec +TOTAL : 0.532325 sec INFO: No Floating Point Exceptions have been reported - 2,208,390,386 cycles # 2.919 GHz - 3,204,166,788 instructions # 1.45 insn per cycle - 0.815663809 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,205,625,214 cycles # 2.868 GHz + 3,174,502,414 instructions # 1.44 insn per cycle + 0.825987629 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 216 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 4.313472e+00 Avg ME (F77/GPU) = 4.3134711012809239 Relative difference = 2.0835166567625394e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.637772e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.674252e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.674252e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.606903e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.644535e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.644535e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 6.510565 sec +TOTAL : 6.677680 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 19,507,805,821 cycles # 2.995 GHz - 49,956,387,381 instructions # 2.56 insn per cycle - 6.515739319 seconds time elapsed + 19,666,494,079 cycles # 2.940 GHz + 50,081,060,677 instructions # 2.55 insn per cycle + 6.689882991 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 599) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -104,8 +104,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -113,24 +113,24 @@ Avg ME (F77/C++) = 4.3134711778082178 Relative difference = 1.906102050071626e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.876906e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.002678e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.002678e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.871340e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.003903e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.003903e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.752629 sec +TOTAL : 3.840726 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 10,992,095,765 cycles # 2.926 GHz - 29,099,784,091 instructions # 2.65 insn per cycle - 3.757823325 seconds time elapsed + 11,259,304,877 cycles # 2.923 GHz + 29,230,934,183 instructions # 2.60 insn per cycle + 3.852980170 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2807) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -138,8 +138,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -147,24 +147,24 @@ Avg ME (F77/C++) = 4.3134711778082178 Relative difference = 1.906102050071626e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.824550e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.042218e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.042218e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.726077e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.943109e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.943109e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.849571 sec +TOTAL : 2.970419 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 8,040,596,401 cycles # 2.817 GHz - 15,172,177,342 instructions # 1.89 insn per cycle - 2.854978145 seconds time elapsed + 8,229,432,856 cycles # 2.759 GHz + 15,297,097,015 instructions # 1.86 insn per cycle + 2.983820409 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3202) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -172,8 +172,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -181,24 +181,24 @@ Avg ME (F77/C++) = 4.3134712319139954 Relative difference = 1.7806676491157786e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.946624e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.177226e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.177226e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.908170e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.147639e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.147639e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 2.763530 sec +TOTAL : 2.839910 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 7,772,626,027 cycles # 2.808 GHz - 14,479,384,179 instructions # 1.86 insn per cycle - 2.768634488 seconds time elapsed + 7,866,112,540 cycles # 2.759 GHz + 14,608,431,526 instructions # 1.86 insn per cycle + 2.852893659 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2774) (512y: 304) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -206,8 +206,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 @@ -215,24 +215,24 @@ Avg ME (F77/C++) = 4.3134712319139954 Relative difference = 1.7806676491157786e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_HEFT_GG_BBX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.163794e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.307782e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.307782e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.030076e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.169205e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.169205e+05 ) sec^-1 MeanMatrixElemValue = ( 7.148017e+00 +- 1.609110e-01 ) GeV^0 -TOTAL : 3.421119 sec +TOTAL : 3.616163 sec INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - 6,532,980,349 cycles # 1.907 GHz - 9,893,746,394 instructions # 1.51 insn per cycle - 3.426456301 seconds time elapsed + 6,699,969,895 cycles # 1.847 GHz + 10,018,865,936 instructions # 1.50 insn per cycle + 3.629335211 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1565) (512y: 216) (512z: 2217) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 4 channels { no-multichannel : 512 } @@ -240,8 +240,8 @@ INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW DEBUG: MEK (channelid array) processed 512 events across 4 channels { 1 : 128, 2 : 128, 3 : 128, 4 : 128 } INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/heft_gg_bb.mad/SubProcesses/P1_gg_bbx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW Avg ME (C++/C++) = 4.313472e+00 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd0.txt index bea3e3659..7707f676a 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:02:20 +DATE: 2024-09-15_12:18:46 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.775059e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.792209e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.795305e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.767516e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.784818e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.787795e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.465694 sec +TOTAL : 0.470421 sec INFO: No Floating Point Exceptions have been reported - 2,004,061,261 cycles # 2.915 GHz - 2,971,857,164 instructions # 1.48 insn per cycle - 0.744562845 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 + 1,978,272,924 cycles # 2.864 GHz + 2,912,164,766 instructions # 1.47 insn per cycle + 0.749211691 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.091435e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.188484e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.195415e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.005244e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.117313e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.126114e+05 ) sec^-1 MeanMatrixElemValue = ( 8.048215e-03 +- 4.042405e-03 ) GeV^-4 -TOTAL : 0.480494 sec +TOTAL : 0.483026 sec INFO: No Floating Point Exceptions have been reported - 2,068,696,668 cycles # 2.915 GHz - 3,082,017,608 instructions # 1.49 insn per cycle - 0.767061276 seconds time elapsed + 2,024,260,948 cycles # 2.878 GHz + 3,029,497,927 instructions # 1.50 insn per cycle + 0.762830166 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127459e-06 Avg ME (F77/GPU) = 8.1274562860176604E-006 Relative difference = 3.3392753366481633e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.487038e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.490402e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.490402e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.405701e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.409074e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.409074e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.153531 sec +TOTAL : 0.157165 sec INFO: No Floating Point Exceptions have been reported - 468,548,605 cycles # 2.990 GHz - 1,389,841,452 instructions # 2.97 insn per cycle - 0.157176483 seconds time elapsed + 467,074,127 cycles # 2.919 GHz + 1,389,682,298 instructions # 2.98 insn per cycle + 0.160520641 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3908) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860167185E-006 Relative difference = 3.339276495559746e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.658870e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.671057e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.671057e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.459230e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.470849e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.470849e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.081219 sec +TOTAL : 0.083614 sec INFO: No Floating Point Exceptions have been reported - 240,143,250 cycles # 2.847 GHz - 693,085,573 instructions # 2.89 insn per cycle - 0.084894638 seconds time elapsed + 239,038,405 cycles # 2.765 GHz + 692,921,675 instructions # 2.90 insn per cycle + 0.087016440 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 9483) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860167168E-006 Relative difference = 3.3392764976441195e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.451702e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.457378e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.457378e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.419984e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.425694e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.425694e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.038390 sec +TOTAL : 0.039288 sec INFO: No Floating Point Exceptions have been reported - 114,533,313 cycles # 2.750 GHz - 258,003,017 instructions # 2.25 insn per cycle - 0.042202043 seconds time elapsed + 113,366,397 cycles # 2.696 GHz + 257,996,166 instructions # 2.28 insn per cycle + 0.042698199 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8503) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.668827e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.676697e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.676697e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.624961e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.632288e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.632288e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.033710 sec +TOTAL : 0.034517 sec INFO: No Floating Point Exceptions have been reported - 102,401,077 cycles # 2.773 GHz - 240,000,244 instructions # 2.34 insn per cycle - 0.037486472 seconds time elapsed + 101,263,068 cycles # 2.711 GHz + 239,969,377 instructions # 2.37 insn per cycle + 0.037861089 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8140) (512y: 150) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.238178e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.244573e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.244573e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.199166e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.204857e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.204857e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.044867 sec +TOTAL : 0.046301 sec INFO: No Floating Point Exceptions have been reported - 89,835,188 cycles # 1.864 GHz - 134,305,795 instructions # 1.50 insn per cycle - 0.048794310 seconds time elapsed + 89,031,390 cycles # 1.806 GHz + 134,346,666 instructions # 1.51 insn per cycle + 0.049794003 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1943) (512y: 126) (512z: 7090) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd1.txt index a1c588c09..ca3a407fd 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:02:31 +DATE: 2024-09-15_12:18:57 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.822628e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.840741e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.844507e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.802842e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.821481e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.824642e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.465549 sec +TOTAL : 0.470683 sec INFO: No Floating Point Exceptions have been reported - 2,003,972,246 cycles # 2.916 GHz - 2,932,804,269 instructions # 1.46 insn per cycle - 0.743970096 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 1 + 1,990,204,132 cycles # 2.870 GHz + 2,908,985,105 instructions # 1.46 insn per cycle + 0.750697991 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.175681e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.275605e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.282748e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.083966e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.205394e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.213656e+05 ) sec^-1 MeanMatrixElemValue = ( 8.048215e-03 +- 4.042405e-03 ) GeV^-4 -TOTAL : 0.480908 sec +TOTAL : 0.487582 sec INFO: No Floating Point Exceptions have been reported - 2,062,625,343 cycles # 2.927 GHz - 3,103,034,956 instructions # 1.50 insn per cycle - 0.761786052 seconds time elapsed + 2,025,056,560 cycles # 2.852 GHz + 2,989,421,142 instructions # 1.48 insn per cycle + 0.769117174 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127459e-06 Avg ME (F77/GPU) = 8.1274562860176604E-006 Relative difference = 3.3392753366481633e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.505070e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.508741e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.508741e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.394566e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.397741e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.397741e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.152229 sec +TOTAL : 0.157033 sec INFO: No Floating Point Exceptions have been reported - 465,988,139 cycles # 3.002 GHz - 1,385,168,372 instructions # 2.97 insn per cycle - 0.155892961 seconds time elapsed + 465,720,728 cycles # 2.911 GHz + 1,385,003,144 instructions # 2.97 insn per cycle + 0.160593741 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3796) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860167185E-006 Relative difference = 3.339276495559746e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.681485e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.694162e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.694162e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.474186e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.485931e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.485931e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.080345 sec +TOTAL : 0.082867 sec INFO: No Floating Point Exceptions have been reported - 239,153,178 cycles # 2.865 GHz - 689,108,288 instructions # 2.88 insn per cycle - 0.084004313 seconds time elapsed + 237,575,401 cycles # 2.770 GHz + 689,116,420 instructions # 2.90 insn per cycle + 0.086305788 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 9528) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860167168E-006 Relative difference = 3.3392764976441195e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.478175e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.484010e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.484010e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.436754e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.442531e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.442531e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.037001 sec +TOTAL : 0.038039 sec INFO: No Floating Point Exceptions have been reported - 111,373,310 cycles # 2.769 GHz - 253,520,749 instructions # 2.28 insn per cycle - 0.040765186 seconds time elapsed + 110,520,646 cycles # 2.700 GHz + 253,448,082 instructions # 2.29 insn per cycle + 0.041474271 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8458) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.631032e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.638379e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.638379e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.611056e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.618327e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.618327e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.033662 sec +TOTAL : 0.034052 sec INFO: No Floating Point Exceptions have been reported - 100,161,001 cycles # 2.721 GHz - 235,610,104 instructions # 2.35 insn per cycle - 0.037359987 seconds time elapsed + 98,863,837 cycles # 2.687 GHz + 235,605,174 instructions # 2.38 insn per cycle + 0.037353270 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8098) (512y: 150) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.233910e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.239184e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.239184e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.176506e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.181658e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.181658e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.044222 sec +TOTAL : 0.046442 sec INFO: No Floating Point Exceptions have been reported - 87,663,045 cycles # 1.846 GHz - 129,734,772 instructions # 1.48 insn per cycle - 0.048056644 seconds time elapsed + 86,647,290 cycles # 1.764 GHz + 129,720,267 instructions # 1.50 insn per cycle + 0.049837932 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1899) (512y: 126) (512z: 7094) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562860174791E-006 Relative difference = 3.3392755596761116e-07 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd0.txt index a2f41df6d..0df257cc6 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:02:42 +DATE: 2024-09-15_12:19:09 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.220036e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.228758e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.230706e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.204232e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.214249e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.216451e+04 ) sec^-1 MeanMatrixElemValue = ( 7.188141e-04 +- 6.565202e-04 ) GeV^-4 -TOTAL : 0.469142 sec +TOTAL : 0.474860 sec INFO: No Floating Point Exceptions have been reported - 1,998,351,728 cycles # 2.917 GHz - 2,946,568,597 instructions # 1.47 insn per cycle - 0.742067766 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 + 1,958,003,333 cycles # 2.836 GHz + 2,859,472,548 instructions # 1.46 insn per cycle + 0.747968607 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.043635e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.115608e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.122969e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.933159e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.016706e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.024424e+05 ) sec^-1 MeanMatrixElemValue = ( 8.020494e-03 +- 4.025605e-03 ) GeV^-4 -TOTAL : 0.469969 sec +TOTAL : 0.477251 sec INFO: No Floating Point Exceptions have been reported - 1,999,338,774 cycles # 2.916 GHz - 2,967,297,221 instructions # 1.48 insn per cycle - 0.742840858 seconds time elapsed + 1,992,584,596 cycles # 2.867 GHz + 2,884,692,368 instructions # 1.45 insn per cycle + 0.751767434 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127250e-06 Avg ME (F77/GPU) = 8.1272869669930272E-006 Relative difference = 4.548524165778887e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.525411e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.528893e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.528893e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.431583e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.434922e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.434922e+03 ) sec^-1 MeanMatrixElemValue = ( 7.177153e-04 +- 6.554185e-04 ) GeV^-4 -TOTAL : 0.151823 sec +TOTAL : 0.155945 sec INFO: No Floating Point Exceptions have been reported - 463,685,635 cycles # 2.993 GHz - 1,381,979,905 instructions # 2.98 insn per cycle - 0.155507501 seconds time elapsed + 462,855,819 cycles # 2.915 GHz + 1,381,844,785 instructions # 2.99 insn per cycle + 0.159290331 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3058) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127811e-06 Avg ME (F77/C++) = 8.1278105271212486E-006 Relative difference = 5.8180333155894157e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.230460e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.234563e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.234563e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.210882e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.215211e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.215211e+04 ) sec^-1 MeanMatrixElemValue = ( 7.177152e-04 +- 6.554185e-04 ) GeV^-4 -TOTAL : 0.044834 sec +TOTAL : 0.045512 sec INFO: No Floating Point Exceptions have been reported - 132,674,412 cycles # 2.762 GHz - 372,118,908 instructions # 2.80 insn per cycle - 0.048600516 seconds time elapsed + 131,360,157 cycles # 2.718 GHz + 372,013,509 instructions # 2.83 insn per cycle + 0.048801319 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:10141) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127809e-06 Avg ME (F77/C++) = 8.1278090510674588E-006 Relative difference = 6.2830535070193674e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.857674e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.882410e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.882410e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.769306e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.791871e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.791871e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165746e-04 +- 6.542823e-04 ) GeV^-4 -TOTAL : 0.020489 sec +TOTAL : 0.021120 sec INFO: No Floating Point Exceptions have been reported - 65,153,175 cycles # 2.750 GHz - 142,867,018 instructions # 2.19 insn per cycle - 0.024228257 seconds time elapsed + 64,157,831 cycles # 2.680 GHz + 142,829,765 instructions # 2.23 insn per cycle + 0.024479209 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 9251) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275366216540664E-006 Relative difference = 4.655111786058001e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.178975e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.210365e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.210365e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.078002e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.105354e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.105354e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165746e-04 +- 6.542823e-04 ) GeV^-4 -TOTAL : 0.018701 sec +TOTAL : 0.019156 sec INFO: No Floating Point Exceptions have been reported - 59,922,348 cycles # 2.743 GHz - 132,780,375 instructions # 2.22 insn per cycle - 0.022373587 seconds time elapsed + 59,143,033 cycles # 2.685 GHz + 132,774,537 instructions # 2.24 insn per cycle + 0.022562262 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8963) (512y: 28) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275366216540664E-006 Relative difference = 4.655111786058001e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.404211e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.426424e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.426424e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.363857e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.386270e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.386270e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165747e-04 +- 6.542824e-04 ) GeV^-4 -TOTAL : 0.024073 sec +TOTAL : 0.024531 sec INFO: No Floating Point Exceptions have been reported - 52,328,028 cycles # 1.905 GHz - 79,593,074 instructions # 1.52 insn per cycle - 0.028041224 seconds time elapsed + 51,349,038 cycles # 1.867 GHz + 79,557,658 instructions # 1.55 insn per cycle + 0.028087213 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2834) (512y: 32) (512z: 7442) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275369863475849E-006 Relative difference = 1.6797726498700304e-09 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd1.txt index f5309d624..1f9290161 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:02:52 +DATE: 2024-09-15_12:19:19 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.247820e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.258266e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.260209e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.234747e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.244150e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.246143e+04 ) sec^-1 MeanMatrixElemValue = ( 7.188141e-04 +- 6.565202e-04 ) GeV^-4 -TOTAL : 0.472822 sec +TOTAL : 0.473072 sec INFO: No Floating Point Exceptions have been reported - 2,009,923,207 cycles # 2.920 GHz - 2,890,056,049 instructions # 1.44 insn per cycle - 0.745979682 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 1 + 1,983,051,703 cycles # 2.868 GHz + 2,920,120,611 instructions # 1.47 insn per cycle + 0.748230768 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 8.160560e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 8.234872e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 8.242045e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.099236e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 8.191571e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 8.199199e+05 ) sec^-1 MeanMatrixElemValue = ( 8.020496e-03 +- 4.025606e-03 ) GeV^-4 -TOTAL : 0.469871 sec +TOTAL : 0.474597 sec INFO: No Floating Point Exceptions have been reported - 2,012,230,071 cycles # 2.932 GHz - 2,945,579,242 instructions # 1.46 insn per cycle - 0.743137766 seconds time elapsed + 1,988,967,454 cycles # 2.876 GHz + 2,944,964,203 instructions # 1.48 insn per cycle + 0.748107743 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127250e-06 Avg ME (F77/GPU) = 8.1272866419447706E-006 Relative difference = 4.508529302013153e-06 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.539442e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.543006e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.543006e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.448809e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.452114e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.452114e+03 ) sec^-1 MeanMatrixElemValue = ( 7.177153e-04 +- 6.554185e-04 ) GeV^-4 -TOTAL : 0.150565 sec +TOTAL : 0.154406 sec INFO: No Floating Point Exceptions have been reported - 461,456,563 cycles # 3.002 GHz - 1,376,868,974 instructions # 2.98 insn per cycle - 0.154279891 seconds time elapsed + 460,841,033 cycles # 2.931 GHz + 1,376,637,796 instructions # 2.99 insn per cycle + 0.157690889 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2930) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127811e-06 Avg ME (F77/C++) = 8.1278105271212486E-006 Relative difference = 5.8180333155894157e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.248007e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.252977e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.252977e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.217964e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.222354e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.222354e+04 ) sec^-1 MeanMatrixElemValue = ( 7.177152e-04 +- 6.554185e-04 ) GeV^-4 -TOTAL : 0.043577 sec +TOTAL : 0.044518 sec INFO: No Floating Point Exceptions have been reported - 130,400,124 cycles # 2.789 GHz - 367,239,733 instructions # 2.82 insn per cycle - 0.047312650 seconds time elapsed + 129,447,390 cycles # 2.729 GHz + 367,192,934 instructions # 2.84 insn per cycle + 0.047990838 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4:10124) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127809e-06 Avg ME (F77/C++) = 8.1278090510674588E-006 Relative difference = 6.2830535070193674e-09 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.757273e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.781001e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.781001e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.769546e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.792490e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.792490e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165746e-04 +- 6.542823e-04 ) GeV^-4 -TOTAL : 0.020362 sec +TOTAL : 0.020349 sec INFO: No Floating Point Exceptions have been reported - 63,133,267 cycles # 2.675 GHz - 138,046,859 instructions # 2.19 insn per cycle - 0.024144110 seconds time elapsed + 62,145,033 cycles # 2.684 GHz + 138,048,264 instructions # 2.22 insn per cycle + 0.023682982 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 9205) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275366216540664E-006 Relative difference = 4.655111786058001e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.124081e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.151751e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.151751e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.058079e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.086570e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.086570e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165746e-04 +- 6.542823e-04 ) GeV^-4 -TOTAL : 0.018102 sec +TOTAL : 0.018477 sec INFO: No Floating Point Exceptions have been reported - 57,980,217 cycles # 2.710 GHz - 127,982,392 instructions # 2.21 insn per cycle - 0.021901107 seconds time elapsed + 56,677,502 cycles # 2.660 GHz + 127,963,925 instructions # 2.26 insn per cycle + 0.021825959 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8919) (512y: 28) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275366216540664E-006 Relative difference = 4.655111786058001e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.313423e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.333536e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.333536e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.337142e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.358958e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.358958e+04 ) sec^-1 MeanMatrixElemValue = ( 7.165747e-04 +- 6.542824e-04 ) GeV^-4 -TOTAL : 0.024267 sec +TOTAL : 0.023953 sec INFO: No Floating Point Exceptions have been reported - 50,462,260 cycles # 1.826 GHz - 74,803,342 instructions # 1.48 insn per cycle - 0.028209078 seconds time elapsed + 48,824,483 cycles # 1.820 GHz + 74,785,723 instructions # 1.53 insn per cycle + 0.027430916 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2789) (512y: 32) (512z: 7444) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127537e-06 Avg ME (F77/C++) = 8.1275369863475849E-006 Relative difference = 1.6797726498700304e-09 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd0.txt index 2890a4230..c9ae97348 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:03:03 +DATE: 2024-09-15_12:19:30 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.776343e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.792993e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.795961e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.749294e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.767595e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.770609e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.466388 sec +TOTAL : 0.467392 sec INFO: No Floating Point Exceptions have been reported - 2,004,927,949 cycles # 2.915 GHz - 2,963,573,449 instructions # 1.48 insn per cycle - 0.745240545 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 1 + 1,983,595,553 cycles # 2.874 GHz + 2,922,486,219 instructions # 1.47 insn per cycle + 0.746529670 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.018693e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.125822e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.133051e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.927630e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.040034e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.047831e+05 ) sec^-1 MeanMatrixElemValue = ( 8.048215e-03 +- 4.042405e-03 ) GeV^-4 -TOTAL : 0.480949 sec +TOTAL : 0.485867 sec INFO: No Floating Point Exceptions have been reported - 2,053,433,685 cycles # 2.916 GHz - 3,058,996,758 instructions # 1.49 insn per cycle - 0.761626110 seconds time elapsed + 2,031,462,606 cycles # 2.875 GHz + 3,037,983,552 instructions # 1.50 insn per cycle + 0.765937206 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127459e-06 Avg ME (F77/GPU) = 8.1274562879405200E-006 Relative difference = 3.3369094561706885e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.464561e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.467953e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.467953e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.382949e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.386200e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.386200e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.154764 sec +TOTAL : 0.158173 sec INFO: No Floating Point Exceptions have been reported - 472,532,900 cycles # 2.991 GHz - 1,398,413,020 instructions # 2.96 insn per cycle - 0.158536821 seconds time elapsed + 471,387,733 cycles # 2.929 GHz + 1,398,281,899 instructions # 2.97 insn per cycle + 0.161473463 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3899) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562948736117E-006 Relative difference = 3.32837900190667e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.897064e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.911051e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.911051e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.673807e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.686050e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.686050e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.078635 sec +TOTAL : 0.080997 sec INFO: No Floating Point Exceptions have been reported - 236,584,738 cycles # 2.891 GHz - 688,026,328 instructions # 2.91 insn per cycle - 0.082347743 seconds time elapsed + 235,160,008 cycles # 2.808 GHz + 688,033,850 instructions # 2.93 insn per cycle + 0.084339129 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 9328) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563175290919E-006 Relative difference = 3.3005037703909805e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.484530e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.491505e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.491505e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.415459e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.422136e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.422136e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.037635 sec +TOTAL : 0.039362 sec INFO: No Floating Point Exceptions have been reported - 113,465,558 cycles # 2.779 GHz - 253,078,905 instructions # 2.23 insn per cycle - 0.041334338 seconds time elapsed + 112,339,380 cycles # 2.665 GHz + 253,052,093 instructions # 2.25 insn per cycle + 0.042695307 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8363) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.662894e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.670459e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.670459e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.648852e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.656658e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.656658e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.033766 sec +TOTAL : 0.034079 sec INFO: No Floating Point Exceptions have been reported - 101,027,313 cycles # 2.738 GHz - 233,681,045 instructions # 2.31 insn per cycle - 0.037444704 seconds time elapsed + 100,217,114 cycles # 2.715 GHz + 233,607,212 instructions # 2.33 insn per cycle + 0.037476380 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 7501) (512y: 146) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.257642e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.262778e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.262778e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.192314e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.197366e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.197366e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.044140 sec +TOTAL : 0.046499 sec INFO: No Floating Point Exceptions have been reported - 90,884,685 cycles # 1.918 GHz - 133,253,680 instructions # 1.47 insn per cycle - 0.048030387 seconds time elapsed + 89,493,670 cycles # 1.812 GHz + 133,128,515 instructions # 1.49 insn per cycle + 0.049962595 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2084) (512y: 122) (512z: 6356) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 diff --git a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd1.txt index 83e47710a..1d81f994c 100644 --- a/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,73 +11,73 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx' -DATE: 2024-09-02_00:03:14 +DATE: 2024-09-15_12:19:41 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 2.806214e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.825154e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.830557e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.765961e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.783708e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.789350e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.465671 sec +TOTAL : 0.474700 sec INFO: No Floating Point Exceptions have been reported - 2,001,070,781 cycles # 2.911 GHz - 2,925,166,809 instructions # 1.46 insn per cycle - 0.744689271 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 1 + 1,974,719,372 cycles # 2.833 GHz + 2,899,642,626 instructions # 1.47 insn per cycle + 0.754986373 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 1 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 255 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ......................................................................... -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 64 256 1 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 7.157504e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.254965e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.263055e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.058757e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.171730e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.179415e+05 ) sec^-1 MeanMatrixElemValue = ( 8.048215e-03 +- 4.042405e-03 ) GeV^-4 -TOTAL : 0.485337 sec +TOTAL : 0.484755 sec INFO: No Floating Point Exceptions have been reported - 2,060,668,286 cycles # 2.923 GHz - 3,043,410,338 instructions # 1.48 insn per cycle - 0.766773978 seconds time elapsed + 2,032,400,386 cycles # 2.878 GHz + 3,034,442,470 instructions # 1.49 insn per cycle + 0.765490241 seconds time elapsed ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -85,33 +85,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 8.127459e-06 Avg ME (F77/GPU) = 8.1274562879405200E-006 Relative difference = 3.3369094561706885e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 3.456469e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.459995e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.459995e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.419840e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.423095e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.423095e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.154174 sec +TOTAL : 0.155760 sec INFO: No Floating Point Exceptions have been reported - 468,802,292 cycles # 2.980 GHz - 1,393,811,967 instructions # 2.97 insn per cycle - 0.157901348 seconds time elapsed + 467,249,665 cycles # 2.946 GHz + 1,393,566,061 instructions # 2.98 insn per cycle + 0.159156822 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3800) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -119,31 +119,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274562948736117E-006 Relative difference = 3.32837900190667e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.799064e+03 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.811422e+03 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.811422e+03 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.647634e+03 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.659890e+03 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.659890e+03 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.078911 sec +TOTAL : 0.080628 sec INFO: No Floating Point Exceptions have been reported - 235,085,555 cycles # 2.865 GHz - 684,192,560 instructions # 2.91 insn per cycle - 0.082631566 seconds time elapsed + 234,377,416 cycles # 2.808 GHz + 684,139,763 instructions # 2.92 insn per cycle + 0.083918243 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 9361) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -151,31 +151,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563175290919E-006 Relative difference = 3.3005037703909805e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.457620e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.463500e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.463500e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.444361e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.450464e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.450464e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.037503 sec +TOTAL : 0.037847 sec INFO: No Floating Point Exceptions have been reported - 111,107,100 cycles # 2.733 GHz - 248,710,507 instructions # 2.24 insn per cycle - 0.041153089 seconds time elapsed + 110,057,998 cycles # 2.704 GHz + 248,602,467 instructions # 2.26 insn per cycle + 0.041225455 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 8316) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -183,31 +183,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.611440e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.619238e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.619238e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.658647e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.666343e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.666343e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.034022 sec +TOTAL : 0.033122 sec INFO: No Floating Point Exceptions have been reported - 103,066,093 cycles # 2.763 GHz - 229,322,184 instructions # 2.23 insn per cycle - 0.037860220 seconds time elapsed + 97,824,445 cycles # 2.731 GHz + 229,151,030 instructions # 2.34 insn per cycle + 0.036353420 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 7452) (512y: 146) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -215,31 +215,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 1 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_SMEFTSIM_TOPU3L_MWSCHEME_UFO_GG_TTXTTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.232630e+04 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.237560e+04 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.237560e+04 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.188861e+04 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.193842e+04 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.193842e+04 ) sec^-1 MeanMatrixElemValue = ( 7.185537e-04 +- 6.562553e-04 ) GeV^-4 -TOTAL : 0.044312 sec +TOTAL : 0.046038 sec INFO: No Floating Point Exceptions have been reported - 88,617,933 cycles # 1.864 GHz - 128,655,107 instructions # 1.45 insn per cycle - 0.048048536 seconds time elapsed + 87,629,988 cycles # 1.795 GHz + 128,556,729 instructions # 1.47 insn per cycle + 0.049600721 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2035) (512y: 122) (512z: 6356) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 72 channels { no-multichannel : 512 } @@ -247,8 +247,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 72 channels { 1 : 32, 2 : 32, 3 : 32, 4 : 32, 5 : 32, 6 : 32, 7 : 32, 8 : 32, 9 : 32, 10 : 32, 11 : 32, 12 : 32, 13 : 32, 14 : 32, 15 : 32, 16 : 32 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/smeft_gg_tttt.mad/SubProcesses/P1_gg_ttxttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 8.127459e-06 Avg ME (F77/C++) = 8.1274563450143301E-006 Relative difference = 3.266686019634872e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd0.txt index 617b4177f..808bf6828 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:01:09 +DATE: 2024-09-15_12:17:33 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.705939e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.441412e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.886849e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.071674e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.333003e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.756234e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.513831 sec +TOTAL : 0.519163 sec INFO: No Floating Point Exceptions have been reported - 2,172,306,307 cycles # 2.920 GHz - 3,124,659,871 instructions # 1.44 insn per cycle - 0.802671698 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,179,162,165 cycles # 2.882 GHz + 3,070,881,799 instructions # 1.41 insn per cycle + 0.812256060 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 130 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477196e-01 Avg ME (F77/GPU) = 0.14771956172964262 Relative difference = 2.590743366698123e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.271347e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.056940e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.056940e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.736392e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.961242e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.961242e+05 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 1.241787 sec +TOTAL : 1.358463 sec INFO: No Floating Point Exceptions have been reported - 3,734,524,562 cycles # 2.996 GHz - 9,729,186,535 instructions # 2.61 insn per cycle - 1.247040130 seconds time elapsed + 3,905,907,731 cycles # 2.851 GHz + 9,863,781,254 instructions # 2.53 insn per cycle + 1.371009162 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 341) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.526302e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.956278e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.956278e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.459599e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.873378e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.873378e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.798035 sec +TOTAL : 0.877453 sec INFO: No Floating Point Exceptions have been reported - 2,324,928,559 cycles # 2.897 GHz - 5,934,379,701 instructions # 2.55 insn per cycle - 0.803329705 seconds time elapsed + 2,486,018,663 cycles # 2.796 GHz + 6,068,811,134 instructions # 2.44 insn per cycle + 0.890013058 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1369) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.269779e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.324433e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.324433e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.202336e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.241982e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.241982e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.572529 sec +TOTAL : 0.633614 sec INFO: No Floating Point Exceptions have been reported - 1,662,682,093 cycles # 2.881 GHz - 3,316,788,109 instructions # 1.99 insn per cycle - 0.577756787 seconds time elapsed + 1,818,277,006 cycles # 2.816 GHz + 3,450,832,845 instructions # 1.90 insn per cycle + 0.646259584 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1499) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.280934e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.365920e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.365920e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.283565e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.391222e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.391222e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.571816 sec +TOTAL : 0.617501 sec INFO: No Floating Point Exceptions have been reported - 1,616,508,739 cycles # 2.804 GHz - 3,286,225,269 instructions # 2.03 insn per cycle - 0.577076218 seconds time elapsed + 1,780,688,704 cycles # 2.829 GHz + 3,420,263,634 instructions # 1.92 insn per cycle + 0.630172459 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1375) (512y: 96) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.213094e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.193189e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.193189e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.121818e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.051040e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.051040e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.586010 sec +TOTAL : 0.653754 sec INFO: No Floating Point Exceptions have been reported - 1,368,385,365 cycles # 2.316 GHz - 2,425,788,088 instructions # 1.77 insn per cycle - 0.591541683 seconds time elapsed + 1,527,075,900 cycles # 2.294 GHz + 2,560,289,188 instructions # 1.68 insn per cycle + 0.666212420 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 580) (512y: 60) (512z: 1021) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd1.txt index b0f30d9af..06cbb3e92 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:01:21 +DATE: 2024-09-15_12:17:46 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.832298e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.616304e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.132808e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.969739e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.449933e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.971179e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.513767 sec +TOTAL : 0.523956 sec INFO: No Floating Point Exceptions have been reported - 2,171,398,785 cycles # 2.919 GHz - 3,102,319,188 instructions # 1.43 insn per cycle - 0.802857401 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,197,273,631 cycles # 2.867 GHz + 3,116,260,127 instructions # 1.42 insn per cycle + 0.822598423 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477196e-01 Avg ME (F77/GPU) = 0.14771956172964262 Relative difference = 2.590743366698123e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.288371e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.060959e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.060959e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.011162e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.031790e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.031790e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 1.237288 sec +TOTAL : 1.321281 sec INFO: No Floating Point Exceptions have been reported - 3,712,284,308 cycles # 2.989 GHz - 9,611,420,819 instructions # 2.59 insn per cycle - 1.242501765 seconds time elapsed + 3,893,594,822 cycles # 2.920 GHz + 9,744,555,445 instructions # 2.50 insn per cycle + 1.334263922 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 359) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.474254e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.878832e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.878832e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.381914e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.838565e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.838565e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.822207 sec +TOTAL : 0.917902 sec INFO: No Floating Point Exceptions have been reported - 2,343,690,158 cycles # 2.835 GHz - 5,879,796,075 instructions # 2.51 insn per cycle - 0.827511338 seconds time elapsed + 2,659,815,270 cycles # 2.862 GHz + 6,026,660,919 instructions # 2.27 insn per cycle + 0.930359460 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1335) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.220023e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.260647e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.260647e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.192597e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.249251e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.249251e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.585099 sec +TOTAL : 0.636612 sec INFO: No Floating Point Exceptions have been reported - 1,645,862,133 cycles # 2.790 GHz - 3,288,630,162 instructions # 2.00 insn per cycle - 0.590634091 seconds time elapsed + 1,830,188,885 cycles # 2.821 GHz + 3,421,758,036 instructions # 1.87 insn per cycle + 0.649438298 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1436) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.298542e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.412196e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.412196e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.271531e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.393290e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.393290e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.568844 sec +TOTAL : 0.619901 sec INFO: No Floating Point Exceptions have been reported - 1,610,064,623 cycles # 2.808 GHz - 3,262,929,746 instructions # 2.03 insn per cycle - 0.574076244 seconds time elapsed + 1,782,873,131 cycles # 2.820 GHz + 3,395,941,059 instructions # 1.90 insn per cycle + 0.632832806 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1328) (512y: 96) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.203373e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.175027e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.175027e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.134142e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.070820e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.070820e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.587261 sec +TOTAL : 0.650853 sec INFO: No Floating Point Exceptions have been reported - 1,373,579,028 cycles # 2.321 GHz - 2,411,054,137 instructions # 1.76 insn per cycle - 0.592531349 seconds time elapsed + 1,547,796,135 cycles # 2.334 GHz + 2,545,431,106 instructions # 1.64 insn per cycle + 0.664117617 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 547) (512y: 60) (512z: 1007) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956172964268 Relative difference = 2.59074336294025e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd0.txt index ae21b45fb..6bbc9fb0d 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:01:34 +DATE: 2024-09-15_12:17:58 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.172680e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.277446e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.670009e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.000684e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.992629e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.388281e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486732e-01 +- 3.293572e-05 ) GeV^0 -TOTAL : 0.476855 sec +TOTAL : 0.488697 sec INFO: No Floating Point Exceptions have been reported - 2,080,048,082 cycles # 2.923 GHz - 2,934,470,906 instructions # 1.41 insn per cycle - 0.769357298 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,047,674,909 cycles # 2.864 GHz + 2,921,802,724 instructions # 1.43 insn per cycle + 0.773667864 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 97 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477195e-01 Avg ME (F77/GPU) = 0.14771956735057756 Relative difference = 4.559355911674916e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.341262e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.072834e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.072834e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.029870e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.042886e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.042886e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293563e-05 ) GeV^0 -TOTAL : 1.210080 sec +TOTAL : 1.272870 sec INFO: No Floating Point Exceptions have been reported - 3,649,824,194 cycles # 3.005 GHz - 9,602,319,220 instructions # 2.63 insn per cycle - 1.215028903 seconds time elapsed + 3,752,313,957 cycles # 2.930 GHz + 9,659,106,684 instructions # 2.57 insn per cycle + 1.281538641 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 463) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956094773486 Relative difference = 2.643675256627469e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.253255e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.405386e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.405386e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.197021e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.333033e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.333033e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293563e-05 ) GeV^0 -TOTAL : 0.552399 sec +TOTAL : 0.588107 sec INFO: No Floating Point Exceptions have been reported - 1,632,093,899 cycles # 2.932 GHz - 3,968,324,524 instructions # 2.43 insn per cycle - 0.557382299 seconds time elapsed + 1,715,029,446 cycles # 2.877 GHz + 4,025,277,973 instructions # 2.35 insn per cycle + 0.596790312 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1579) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955861942843 Relative difference = 2.80129187869649e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.047638e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.394338e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.394338e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.961392e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.263984e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.263984e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293562e-05 ) GeV^0 -TOTAL : 0.429395 sec +TOTAL : 0.463961 sec INFO: No Floating Point Exceptions have been reported - 1,250,766,491 cycles # 2.884 GHz - 2,498,057,764 instructions # 2.00 insn per cycle - 0.434425808 seconds time elapsed + 1,335,854,072 cycles # 2.831 GHz + 2,555,445,671 instructions # 1.91 insn per cycle + 0.472547002 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1924) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955698961392 Relative difference = 2.9116235141448046e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.179958e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.709899e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.709899e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.064902e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.593039e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.593039e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293562e-05 ) GeV^0 -TOTAL : 0.416325 sec +TOTAL : 0.451960 sec INFO: No Floating Point Exceptions have been reported - 1,219,121,155 cycles # 2.899 GHz - 2,472,105,838 instructions # 2.03 insn per cycle - 0.421331232 seconds time elapsed + 1,308,601,918 cycles # 2.845 GHz + 2,529,434,362 instructions # 1.93 insn per cycle + 0.460618771 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1867) (512y: 1) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955698961392 Relative difference = 2.9116235141448046e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.995188e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.099116e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.099116e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.884808e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.904943e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.904943e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293561e-05 ) GeV^0 -TOTAL : 0.438175 sec +TOTAL : 0.475883 sec INFO: No Floating Point Exceptions have been reported - 1,071,487,340 cycles # 2.420 GHz - 2,074,189,485 instructions # 1.94 insn per cycle - 0.443244948 seconds time elapsed + 1,154,211,341 cycles # 2.384 GHz + 2,131,381,757 instructions # 1.85 insn per cycle + 0.484642507 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1011) (512y: 5) (512z: 1292) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955262403935 Relative difference = 3.207154680524219e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd1.txt index 3f432b655..5f533fb3c 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:01:45 +DATE: 2024-09-15_12:18:10 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 1.154808e+08 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.194582e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.565830e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.019765e+08 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.955728e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.339790e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486732e-01 +- 3.293572e-05 ) GeV^0 -TOTAL : 0.479664 sec +TOTAL : 0.485800 sec INFO: No Floating Point Exceptions have been reported - 2,066,272,973 cycles # 2.913 GHz - 2,959,541,266 instructions # 1.43 insn per cycle - 0.768366251 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,046,836,184 cycles # 2.868 GHz + 2,861,763,521 instructions # 1.40 insn per cycle + 0.770456449 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 86 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477195e-01 Avg ME (F77/GPU) = 0.14771956525510177 Relative difference = 4.4175008557828484e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.348696e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.078278e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.078278e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 9.176079e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.058039e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.058039e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293563e-05 ) GeV^0 -TOTAL : 1.208511 sec +TOTAL : 1.251903 sec INFO: No Floating Point Exceptions have been reported - 3,615,745,577 cycles # 2.981 GHz - 9,472,516,585 instructions # 2.62 insn per cycle - 1.213452227 seconds time elapsed + 3,703,836,740 cycles # 2.940 GHz + 9,528,821,992 instructions # 2.57 insn per cycle + 1.260572218 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 367) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956094773486 Relative difference = 2.643675256627469e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.256979e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.415783e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.415783e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.192175e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.322296e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.322296e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293563e-05 ) GeV^0 -TOTAL : 0.551273 sec +TOTAL : 0.587889 sec INFO: No Floating Point Exceptions have been reported - 1,631,110,236 cycles # 2.935 GHz - 3,934,262,602 instructions # 2.41 insn per cycle - 0.556359995 seconds time elapsed + 1,712,573,858 cycles # 2.874 GHz + 3,991,164,090 instructions # 2.33 insn per cycle + 0.596469979 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1517) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955861942843 Relative difference = 2.80129187869649e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.079393e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.400939e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.400939e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.984131e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.291891e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.291891e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293562e-05 ) GeV^0 -TOTAL : 0.425944 sec +TOTAL : 0.460621 sec INFO: No Floating Point Exceptions have been reported - 1,245,519,260 cycles # 2.895 GHz - 2,482,547,459 instructions # 1.99 insn per cycle - 0.430910478 seconds time elapsed + 1,332,768,943 cycles # 2.844 GHz + 2,539,760,549 instructions # 1.91 insn per cycle + 0.469223881 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1815) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955698961392 Relative difference = 2.9116235141448046e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.175230e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.704334e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.704334e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.068338e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.608348e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.608348e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293562e-05 ) GeV^0 -TOTAL : 0.415401 sec +TOTAL : 0.451660 sec INFO: No Floating Point Exceptions have been reported - 1,217,462,881 cycles # 2.901 GHz - 2,459,454,464 instructions # 2.02 insn per cycle - 0.420406157 seconds time elapsed + 1,303,705,490 cycles # 2.835 GHz + 2,516,660,988 instructions # 1.93 insn per cycle + 0.460426647 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1776) (512y: 1) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955698961392 Relative difference = 2.9116235141448046e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.042589e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.197180e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.197180e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.904674e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.952335e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.952335e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486735e-01 +- 3.293561e-05 ) GeV^0 -TOTAL : 0.431010 sec +TOTAL : 0.470523 sec INFO: No Floating Point Exceptions have been reported - 1,065,793,790 cycles # 2.448 GHz - 2,057,938,519 instructions # 1.93 insn per cycle - 0.435976515 seconds time elapsed + 1,148,816,748 cycles # 2.401 GHz + 2,115,600,264 instructions # 1.84 insn per cycle + 0.478989217 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 906) (512y: 5) (512z: 1273) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771955262403935 Relative difference = 3.207154680524219e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd0.txt index b59eca5ee..45ada3a90 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:01:56 +DATE: 2024-09-15_12:18:21 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.711022e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.444825e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.891145e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.081665e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.353918e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.800720e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.510096 sec +TOTAL : 0.522074 sec INFO: No Floating Point Exceptions have been reported - 2,197,599,535 cycles # 2.926 GHz - 3,114,723,183 instructions # 1.42 insn per cycle - 0.808466821 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,188,417,927 cycles # 2.886 GHz + 3,109,980,535 instructions # 1.42 insn per cycle + 0.814803667 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 130 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477196e-01 Avg ME (F77/GPU) = 0.14771956187351573 Relative difference = 2.5810037581511336e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.059352e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.033640e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.033640e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.910495e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.017920e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.017920e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 1.268650 sec +TOTAL : 1.334640 sec INFO: No Floating Point Exceptions have been reported - 3,771,710,829 cycles # 2.962 GHz - 9,754,505,592 instructions # 2.59 insn per cycle - 1.273897417 seconds time elapsed + 3,942,717,867 cycles # 2.929 GHz + 9,888,397,619 instructions # 2.51 insn per cycle + 1.346816311 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 341) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956645541506 Relative difference = 2.270828308707201e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.558332e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.007967e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.007967e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.550381e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.026476e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.026476e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.783008 sec +TOTAL : 0.835395 sec INFO: No Floating Point Exceptions have been reported - 2,310,402,593 cycles # 2.933 GHz - 5,917,549,361 instructions # 2.56 insn per cycle - 0.788339620 seconds time elapsed + 2,474,407,927 cycles # 2.921 GHz + 6,051,781,084 instructions # 2.45 insn per cycle + 0.847852996 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1410) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956645541506 Relative difference = 2.270828308707201e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.331953e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.457739e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.457739e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.251869e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.352067e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.352067e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.560431 sec +TOTAL : 0.625126 sec INFO: No Floating Point Exceptions have been reported - 1,634,630,269 cycles # 2.893 GHz - 3,254,908,835 instructions # 1.99 insn per cycle - 0.565744522 seconds time elapsed + 1,795,351,792 cycles # 2.819 GHz + 3,389,782,871 instructions # 1.89 insn per cycle + 0.637929251 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1567) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.370507e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.529509e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.529509e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.324637e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.489814e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.489814e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.553314 sec +TOTAL : 0.609151 sec INFO: No Floating Point Exceptions have been reported - 1,598,397,792 cycles # 2.865 GHz - 3,210,982,116 instructions # 2.01 insn per cycle - 0.558573463 seconds time elapsed + 1,759,711,411 cycles # 2.834 GHz + 3,345,109,138 instructions # 1.90 insn per cycle + 0.621588850 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1446) (512y: 101) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.239065e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.276775e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.276775e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.155541e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.119089e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.119089e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.581191 sec +TOTAL : 0.645680 sec INFO: No Floating Point Exceptions have been reported - 1,341,912,926 cycles # 2.290 GHz - 2,377,902,713 instructions # 1.77 insn per cycle - 0.586599513 seconds time elapsed + 1,520,276,942 cycles # 2.311 GHz + 2,512,095,426 instructions # 1.65 insn per cycle + 0.658351218 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 768) (512y: 64) (512z: 1063) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 diff --git a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd1.txt index 0761d80f6..635fef145 100644 --- a/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x' -DATE: 2024-09-02_00:02:08 +DATE: 2024-09-15_12:18:34 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 6.786230e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.554941e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.045306e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.163952e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.460728e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.975996e+08 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.511925 sec +TOTAL : 0.521235 sec INFO: No Floating Point Exceptions have been reported - 2,190,313,449 cycles # 2.920 GHz - 3,134,280,951 instructions # 1.43 insn per cycle - 0.807505561 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,178,235,183 cycles # 2.877 GHz + 3,088,126,574 instructions # 1.42 insn per cycle + 0.814490194 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 1.477196e-01 Avg ME (F77/GPU) = 0.14771956187351573 Relative difference = 2.5810037581511336e-07 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 9.171250e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.046529e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.046529e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.905010e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.017534e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.017534e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 1.252183 sec +TOTAL : 1.334358 sec INFO: No Floating Point Exceptions have been reported - 3,761,080,220 cycles # 2.993 GHz - 9,645,091,040 instructions # 2.56 insn per cycle - 1.257461532 seconds time elapsed + 3,930,631,045 cycles # 2.921 GHz + 9,778,615,750 instructions # 2.49 insn per cycle + 1.346795690 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 359) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956645541506 Relative difference = 2.270828308707201e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 1.525381e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.962903e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.962903e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.520527e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.978156e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.978156e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.797796 sec +TOTAL : 0.848228 sec INFO: No Floating Point Exceptions have been reported - 2,292,955,540 cycles # 2.859 GHz - 5,860,568,229 instructions # 2.56 insn per cycle - 0.802900333 seconds time elapsed + 2,460,773,168 cycles # 2.862 GHz + 5,993,984,003 instructions # 2.44 insn per cycle + 0.860657174 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 1368) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956645541506 Relative difference = 2.270828308707201e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.268434e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.328040e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.328040e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.233001e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.325225e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.325225e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.572092 sec +TOTAL : 0.627322 sec INFO: No Floating Point Exceptions have been reported - 1,644,248,919 cycles # 2.852 GHz - 3,218,953,769 instructions # 1.96 insn per cycle - 0.577145152 seconds time elapsed + 1,810,072,132 cycles # 2.832 GHz + 3,352,499,816 instructions # 1.85 insn per cycle + 0.639697989 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1483) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.381298e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.582145e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.582145e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.331445e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.508166e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.508166e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.551151 sec +TOTAL : 0.606762 sec INFO: No Floating Point Exceptions have been reported - 1,601,842,641 cycles # 2.882 GHz - 3,182,853,937 instructions # 1.99 insn per cycle - 0.556446747 seconds time elapsed + 1,747,202,335 cycles # 2.825 GHz + 3,316,993,487 instructions # 1.90 insn per cycle + 0.619170203 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1382) (512y: 101) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_T1T1X_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 2.271455e+06 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.309008e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.309008e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 2.144157e+06 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.097547e+06 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.097547e+06 ) sec^-1 MeanMatrixElemValue = ( 1.486736e-01 +- 3.293564e-05 ) GeV^0 -TOTAL : 0.572096 sec +TOTAL : 0.647875 sec INFO: No Floating Point Exceptions have been reported - 1,360,273,199 cycles # 2.358 GHz - 2,361,960,995 instructions # 1.74 insn per cycle - 0.577285951 seconds time elapsed + 1,527,422,709 cycles # 2.315 GHz + 2,496,191,682 instructions # 1.63 insn per cycle + 0.660479795 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 716) (512y: 64) (512z: 1054) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 6 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 6 channels { 2 : 128, 3 : 96, 4 : 96, 5 : 96, 6 : 96 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_t1t1.mad/SubProcesses/P1_gg_t1t1x/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 1.477196e-01 Avg ME (F77/C++) = 0.14771956674392650 Relative difference = 2.2512972893324335e-07 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd0.txt index aaac9a4e4..0f0996a4b 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:58:46 +DATE: 2024-09-15_12:15:09 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.653027e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.340470e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.925372e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.705596e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.093007e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.806904e+07 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 0.526809 sec +TOTAL : 0.547454 sec INFO: No Floating Point Exceptions have been reported - 2,213,151,288 cycles # 2.920 GHz - 3,205,651,873 instructions # 1.45 insn per cycle - 0.815245250 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,244,643,125 cycles # 2.856 GHz + 3,194,753,552 instructions # 1.42 insn per cycle + 0.844381889 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015836e+00 Avg ME (F77/GPU) = 2.0158358666195562 Relative difference = 6.616631711254798e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.860503e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.908123e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.908123e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.817695e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.865026e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.865026e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 5.740977 sec +TOTAL : 5.917395 sec INFO: No Floating Point Exceptions have been reported - 17,253,451,365 cycles # 3.003 GHz - 45,921,355,629 instructions # 2.66 insn per cycle - 5.746162125 seconds time elapsed + 17,420,747,172 cycles # 2.939 GHz + 46,039,408,535 instructions # 2.64 insn per cycle + 5.929443281 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 622) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194407 Relative difference = 6.616637439061751e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.237581e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.395323e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.395323e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.177458e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.337417e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.337417e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.343336 sec +TOTAL : 3.449474 sec INFO: No Floating Point Exceptions have been reported - 10,011,623,439 cycles # 2.991 GHz - 27,803,676,769 instructions # 2.78 insn per cycle - 3.348521908 seconds time elapsed + 10,167,811,545 cycles # 2.940 GHz + 27,922,488,818 instructions # 2.75 insn per cycle + 3.461267593 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2533) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194411 Relative difference = 6.616637417031725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.131063e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.533661e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.533661e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.001375e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.394642e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.394642e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.150729 sec +TOTAL : 2.246102 sec INFO: No Floating Point Exceptions have been reported - 6,070,393,401 cycles # 2.817 GHz - 12,586,845,951 instructions # 2.07 insn per cycle - 2.155997201 seconds time elapsed + 6,225,214,133 cycles # 2.758 GHz + 12,703,481,596 instructions # 2.04 insn per cycle + 2.257992148 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2620) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.540655e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.005391e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.005391e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.452222e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.920256e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.920256e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 1.997882 sec +TOTAL : 2.070361 sec INFO: No Floating Point Exceptions have been reported - 5,577,536,285 cycles # 2.786 GHz - 12,004,229,035 instructions # 2.15 insn per cycle - 2.003159970 seconds time elapsed + 5,740,692,800 cycles # 2.758 GHz + 12,120,362,498 instructions # 2.11 insn per cycle + 2.082196362 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2363) (512y: 144) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.615033e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.803174e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.803174e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.496236e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.681187e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.681187e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.007089 sec +TOTAL : 3.148263 sec INFO: No Floating Point Exceptions have been reported - 5,749,608,423 cycles # 1.909 GHz - 8,342,953,353 instructions # 1.45 insn per cycle - 3.012371924 seconds time elapsed + 5,893,231,770 cycles # 1.865 GHz + 8,460,083,225 instructions # 1.44 insn per cycle + 3.160116132 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1468) (512y: 122) (512z: 1806) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd1.txt index 378b21a23..b863aa4b8 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:59:11 +DATE: 2024-09-15_12:15:34 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.662858e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.418241e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.001899e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.254248e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.331434e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.002046e+08 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 0.525518 sec +TOTAL : 0.532593 sec INFO: No Floating Point Exceptions have been reported - 2,132,676,957 cycles # 2.812 GHz - 3,121,749,820 instructions # 1.46 insn per cycle - 0.815010260 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,206,521,572 cycles # 2.874 GHz + 3,181,038,873 instructions # 1.44 insn per cycle + 0.824867346 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 212 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_d_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015836e+00 Avg ME (F77/GPU) = 2.0158358666195562 Relative difference = 6.616631711254798e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_d_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.908389e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.958750e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.958750e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.847951e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.897550e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.897550e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 5.599275 sec +TOTAL : 5.824198 sec INFO: No Floating Point Exceptions have been reported - 16,763,422,918 cycles # 2.992 GHz - 44,907,263,948 instructions # 2.68 insn per cycle - 5.604556101 seconds time elapsed + 17,074,611,956 cycles # 2.927 GHz + 45,037,522,622 instructions # 2.64 insn per cycle + 5.835488505 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 566) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194411 Relative difference = 6.616637417031725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.408622e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.585143e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.585143e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.339846e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.517622e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.517622e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.182414 sec +TOTAL : 3.286951 sec INFO: No Floating Point Exceptions have been reported - 9,555,914,308 cycles # 2.999 GHz - 26,687,968,907 instructions # 2.79 insn per cycle - 3.187704655 seconds time elapsed + 9,688,702,526 cycles # 2.938 GHz + 26,805,473,197 instructions # 2.77 insn per cycle + 3.298888236 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2327) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194411 Relative difference = 6.616637417031725e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.659733e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.989188e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.989188e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.556976e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.882070e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.882070e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.355005 sec +TOTAL : 2.448521 sec INFO: No Floating Point Exceptions have been reported - 6,586,794,349 cycles # 2.792 GHz - 14,110,405,758 instructions # 2.14 insn per cycle - 2.360343248 seconds time elapsed + 6,771,268,311 cycles # 2.753 GHz + 14,227,806,494 instructions # 2.10 insn per cycle + 2.460277833 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2704) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.851705e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.216127e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.216127e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.776530e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.130549e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.130549e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.266798 sec +TOTAL : 2.341767 sec INFO: No Floating Point Exceptions have been reported - 6,332,630,844 cycles # 2.788 GHz - 13,705,013,933 instructions # 2.16 insn per cycle - 2.272035255 seconds time elapsed + 6,488,711,878 cycles # 2.758 GHz + 13,822,301,429 instructions # 2.13 insn per cycle + 2.353629315 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2355) (512y: 297) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = DOUBLE (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.432050e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.603910e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.603910e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.365014e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.535721e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.535721e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.161293 sec +TOTAL : 3.263382 sec INFO: No Floating Point Exceptions have been reported - 5,942,810,149 cycles # 1.877 GHz - 10,101,972,904 instructions # 1.70 insn per cycle - 3.166381476 seconds time elapsed + 6,085,804,948 cycles # 1.859 GHz + 10,219,161,569 instructions # 1.68 insn per cycle + 3.275179492 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1318) (512y: 208) (512z: 1986) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_d_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158358666194953 Relative difference = 6.616634729368461e-08 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd0.txt index f9afc129d..cf83c07d4 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:59:36 +DATE: 2024-09-15_12:16:00 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.048309e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.804245e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.916971e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.223710e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.732879e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.860967e+08 ) sec^-1 MeanMatrixElemValue = ( 2.072877e+00 +- 3.361153e-03 ) GeV^0 -TOTAL : 0.487622 sec +TOTAL : 0.489964 sec INFO: No Floating Point Exceptions have been reported - 2,070,419,388 cycles # 2.916 GHz - 2,949,604,523 instructions # 1.42 insn per cycle - 0.768904766 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,041,886,975 cycles # 2.853 GHz + 2,932,689,889 instructions # 1.44 insn per cycle + 0.773926194 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 125 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015841e+00 Avg ME (F77/GPU) = 2.0158787037944421 Relative difference = 1.870375413642407e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.966520e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 2.023235e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 2.023235e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.929290e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.984521e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.984521e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072937e+00 +- 3.361545e-03 ) GeV^0 -TOTAL : 5.417892 sec +TOTAL : 5.538462 sec INFO: No Floating Point Exceptions have been reported - 16,207,150,412 cycles # 2.990 GHz - 45,319,225,618 instructions # 2.80 insn per cycle - 5.422848534 seconds time elapsed + 16,282,391,613 cycles # 2.936 GHz + 45,369,954,990 instructions # 2.79 insn per cycle + 5.546087919 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 600) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015849e+00 Avg ME (F77/C++) = 2.0158491701586172 Relative difference = 8.441039850630506e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.597400e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.936181e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.936181e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.517678e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.857555e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.857555e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072937e+00 +- 3.361544e-03 ) GeV^0 -TOTAL : 2.366627 sec +TOTAL : 2.425578 sec INFO: No Floating Point Exceptions have been reported - 7,070,935,943 cycles # 2.982 GHz - 17,771,231,538 instructions # 2.51 insn per cycle - 2.371927913 seconds time elapsed + 7,146,342,805 cycles # 2.938 GHz + 17,820,817,556 instructions # 2.49 insn per cycle + 2.433499088 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 3136) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015849e+00 Avg ME (F77/C++) = 2.0158486895961687 Relative difference = 1.539816876576819e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.462382e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.622186e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.622186e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.300139e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.447005e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.447005e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 1.325025 sec +TOTAL : 1.366410 sec INFO: No Floating Point Exceptions have been reported - 3,738,303,869 cycles # 2.812 GHz - 8,265,337,032 instructions # 2.21 insn per cycle - 1.330172400 seconds time elapsed + 3,812,530,133 cycles # 2.776 GHz + 8,314,531,864 instructions # 2.18 insn per cycle + 1.374237525 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3369) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015847e+00 Avg ME (F77/C++) = 2.0158474864438176 Relative difference = 2.4130988992271984e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 8.968780e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.027488e+06 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.027488e+06 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 8.645853e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.897799e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.897799e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 1.252562 sec +TOTAL : 1.316285 sec INFO: No Floating Point Exceptions have been reported - 3,553,623,001 cycles # 2.827 GHz - 7,920,395,453 instructions # 2.23 insn per cycle - 1.257589697 seconds time elapsed + 3,675,425,998 cycles # 2.778 GHz + 7,974,219,247 instructions # 2.17 insn per cycle + 1.323972787 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3213) (512y: 20) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015847e+00 Avg ME (F77/C++) = 2.0158474864438176 Relative difference = 2.4130988992271984e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 6.786175e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 7.483095e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 7.483095e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.513578e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 7.178216e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 7.178216e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 1.630134 sec +TOTAL : 1.714470 sec INFO: No Floating Point Exceptions have been reported - 3,247,631,595 cycles # 1.990 GHz - 6,100,927,102 instructions # 1.88 insn per cycle - 1.635147155 seconds time elapsed + 3,315,579,741 cycles # 1.925 GHz + 6,150,343,295 instructions # 1.85 insn per cycle + 1.722857238 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2256) (512y: 24) (512z: 2156) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015848e+00 Avg ME (F77/C++) = 2.0158476348733529 Relative difference = 1.8112806478434436e-07 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd1.txt index 958f80873..60f2dad34 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-01_23:59:56 +DATE: 2024-09-15_12:16:21 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:FLT+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 9.035830e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.802180e+08 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.914241e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 7.969923e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.737348e+08 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.863422e+08 ) sec^-1 MeanMatrixElemValue = ( 2.072877e+00 +- 3.361153e-03 ) GeV^0 -TOTAL : 0.483129 sec +TOTAL : 0.488943 sec INFO: No Floating Point Exceptions have been reported - 2,054,954,765 cycles # 2.911 GHz - 2,972,387,315 instructions # 1.45 insn per cycle - 0.764795813 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,058,928,554 cycles # 2.875 GHz + 2,909,617,560 instructions # 1.41 insn per cycle + 0.773317754 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 124 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_f_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015841e+00 Avg ME (F77/GPU) = 2.0158787037944421 Relative difference = 1.870375413642407e-05 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_f_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.906781e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.962993e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.962993e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.962212e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 2.019252e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 2.019252e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072937e+00 +- 3.361545e-03 ) GeV^0 -TOTAL : 5.586697 sec +TOTAL : 5.446348 sec INFO: No Floating Point Exceptions have been reported - 15,967,526,620 cycles # 2.856 GHz - 44,427,051,711 instructions # 2.78 insn per cycle - 5.591572721 seconds time elapsed + 16,014,544,982 cycles # 2.937 GHz + 44,474,347,041 instructions # 2.78 insn per cycle + 5.454124254 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 533) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015849e+00 Avg ME (F77/C++) = 2.0158491701586172 Relative difference = 8.441039850630506e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.113742e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.566435e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.566435e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.286669e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.759924e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.759924e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072937e+00 +- 3.361544e-03 ) GeV^0 -TOTAL : 2.138442 sec +TOTAL : 2.086643 sec INFO: No Floating Point Exceptions have been reported - 6,100,101,446 cycles # 2.848 GHz - 17,077,931,441 instructions # 2.80 insn per cycle - 2.143473002 seconds time elapsed + 6,135,728,749 cycles # 2.931 GHz + 17,120,648,230 instructions # 2.79 insn per cycle + 2.094524948 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2863) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015849e+00 Avg ME (F77/C++) = 2.0158486895961687 Relative difference = 1.539816876576819e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.782057e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.310209e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.310209e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.052770e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.643067e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.643067e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 1.902526 sec +TOTAL : 1.835441 sec INFO: No Floating Point Exceptions have been reported - 5,024,219,960 cycles # 2.635 GHz - 10,224,646,422 instructions # 2.04 insn per cycle - 1.908281978 seconds time elapsed + 5,101,873,696 cycles # 2.769 GHz + 10,273,156,361 instructions # 2.01 insn per cycle + 1.843297684 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3906) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015847e+00 Avg ME (F77/C++) = 2.0158474864438176 Relative difference = 2.4130988992271984e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.883713e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 6.430713e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 6.430713e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 6.133897e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 6.741009e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 6.741009e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 1.867850 sec +TOTAL : 1.812216 sec INFO: No Floating Point Exceptions have been reported - 4,959,367,813 cycles # 2.649 GHz - 9,995,718,795 instructions # 2.02 insn per cycle - 1.872847397 seconds time elapsed + 5,041,846,676 cycles # 2.771 GHz + 10,042,915,318 instructions # 1.99 insn per cycle + 1.820042823 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 3805) (512y: 2) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015847e+00 Avg ME (F77/C++) = 2.0158474864438176 Relative difference = 2.4130988992271984e-07 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:FLT+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = FLOAT (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[16] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.458764e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.763718e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.763718e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.642094e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.969408e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.969408e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072967e+00 +- 3.361967e-03 ) GeV^0 -TOTAL : 2.437626 sec +TOTAL : 2.363033 sec INFO: No Floating Point Exceptions have been reported - 4,360,017,003 cycles # 1.787 GHz - 8,444,019,774 instructions # 1.94 insn per cycle - 2.442485988 seconds time elapsed + 4,430,997,247 cycles # 1.870 GHz + 8,493,309,798 instructions # 1.92 insn per cycle + 2.370917653 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2744) (512y: 4) (512z: 2754) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_f_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015848e+00 Avg ME (F77/C++) = 2.0158476348733529 Relative difference = 1.8112806478434436e-07 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd0.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd0.txt index 184bc580e..62fab95ac 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd0.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd0.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-02_00:00:18 +DATE: 2024-09-15_12:16:43 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.681342e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.493674e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.010313e+08 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.370448e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.371457e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.004604e+08 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 0.527962 sec +TOTAL : 0.536026 sec INFO: No Floating Point Exceptions have been reported - 2,142,172,279 cycles # 2.815 GHz - 3,110,651,634 instructions # 1.45 insn per cycle - 0.817661924 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 + 2,214,409,122 cycles # 2.867 GHz + 3,163,292,335 instructions # 1.43 insn per cycle + 0.830149622 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 214 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd0/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015836e+00 Avg ME (F77/GPU) = 2.0158358639104246 Relative difference = 6.751024171044779e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd0/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd0/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.743073e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.787260e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.787260e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.787519e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.833765e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.833765e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 6.126680 sec +TOTAL : 6.014473 sec INFO: No Floating Point Exceptions have been reported - 17,463,177,818 cycles # 2.850 GHz - 46,087,857,513 instructions # 2.64 insn per cycle - 6.131880330 seconds time elapsed + 17,675,190,561 cycles # 2.934 GHz + 46,198,484,525 instructions # 2.61 insn per cycle + 6.025789457 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 622) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359218686011 Relative difference = 3.8758807327712803e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.106944e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.265946e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.265946e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.209372e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.373008e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.373008e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.486520 sec +TOTAL : 3.414727 sec INFO: No Floating Point Exceptions have been reported - 9,905,155,322 cycles # 2.838 GHz - 27,598,829,825 instructions # 2.79 insn per cycle - 3.491810860 seconds time elapsed + 10,062,586,014 cycles # 2.937 GHz + 27,715,049,037 instructions # 2.75 insn per cycle + 3.427097999 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2582) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359218686011 Relative difference = 3.8758807327712803e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.849477e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.217209e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.217209e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.030622e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.429639e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.429639e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.271105 sec +TOTAL : 2.231035 sec INFO: No Floating Point Exceptions have been reported - 6,003,648,111 cycles # 2.639 GHz - 12,489,197,646 instructions # 2.08 insn per cycle - 2.276156194 seconds time elapsed + 6,157,448,048 cycles # 2.747 GHz + 12,606,647,104 instructions # 2.05 insn per cycle + 2.242669652 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2777) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 5.363313e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 5.814874e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 5.814874e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 5.510413e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.987462e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.987462e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.063360 sec +TOTAL : 2.049793 sec INFO: No Floating Point Exceptions have been reported - 5,497,285,854 cycles # 2.660 GHz - 11,926,850,128 instructions # 2.17 insn per cycle - 2.068523111 seconds time elapsed + 5,651,790,254 cycles # 2.742 GHz + 12,043,922,780 instructions # 2.13 insn per cycle + 2.061986198 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2522) (512y: 146) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=0] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.420824e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.598692e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.598692e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.559881e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.752268e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.752268e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.174262 sec +TOTAL : 3.093339 sec INFO: No Floating Point Exceptions have been reported - 5,615,505,273 cycles # 1.767 GHz - 8,115,440,716 instructions # 1.45 insn per cycle - 3.179484468 seconds time elapsed + 5,777,925,002 cycles # 1.861 GHz + 8,230,989,757 instructions # 1.42 insn per cycle + 3.105063126 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1671) (512y: 126) (512z: 1866) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd0/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08 diff --git a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd1.txt b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd1.txt index 916e38c1b..bde416a88 100644 --- a/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd1.txt +++ b/epochX/cudacpp/tput/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd1.txt @@ -1,5 +1,5 @@ -Building in /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx +Building in /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx BACKEND=cpp512y (was cppauto) OMPFLAGS= FPTYPE='d' @@ -11,58 +11,58 @@ Building in BUILDDIR=build.auto_d_inl0_hrd0 for tag=512y_d_inl0_hrd0_hasCurand_h make: Nothing to be done for 'gtestlibs'. make USEBUILDDIR=1 BACKEND=cuda -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppnone -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppsse4 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cppavx2 -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512y -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make USEBUILDDIR=1 BACKEND=cpp512z -make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Entering directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' make[1]: Nothing to be done for 'all'. -make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' +make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx' -DATE: 2024-09-02_00:00:44 +DATE: 2024-09-15_12:17:08 On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]: ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CUD:MIX+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) -EvtsPerSec[Rmb+ME] (23) = ( 4.631870e+07 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 9.275543e+07 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 9.856692e+07 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.300920e+07 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 9.324653e+07 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 9.961570e+07 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 0.526521 sec +TOTAL : 0.533607 sec INFO: No Floating Point Exceptions have been reported - 2,129,961,314 cycles # 2.806 GHz - 3,087,664,389 instructions # 1.45 insn per cycle - 0.815795024 seconds time elapsed -runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 + 2,198,649,887 cycles # 2.849 GHz + 3,081,934,025 instructions # 1.40 insn per cycle + 0.827713906 seconds time elapsed +runNcu /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe -p 2048 256 1 ==PROF== Profiling "sigmaKin": launch__registers_per_thread 212 ==PROF== Profiling "sigmaKin": sm__sass_average_branch_targets_threads_uniform.pct 100% ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/runTest_cuda.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -70,33 +70,33 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/check_cuda.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.cuda_m_inl0_hrd1/fcheck_cuda.exe 2 64 2 Avg ME (C++/GPU) = 2.015836e+00 Avg ME (F77/GPU) = 2.0158358639104246 Relative difference = 6.751024171044779e-08 OK (relative difference <= 5E-3) ========================================================================= -Not found: /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd1/check_hip.exe +Not found: /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.hip_m_inl0_hrd1/check_hip.exe ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/none+NAVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD) -EvtsPerSec[Rmb+ME] (23) = ( 1.803541e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 1.850201e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 1.850201e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 1.850472e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 1.899391e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 1.899391e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 5.922063 sec +TOTAL : 5.814253 sec INFO: No Floating Point Exceptions have been reported - 16,951,887,322 cycles # 2.861 GHz - 45,094,274,315 instructions # 2.66 insn per cycle - 5.927079923 seconds time elapsed + 17,118,477,102 cycles # 2.939 GHz + 45,207,445,046 instructions # 2.64 insn per cycle + 5.826249043 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 567) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -104,31 +104,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.none_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359218686011 Relative difference = 3.8758807327712803e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.271198e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.440809e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.440809e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.320488e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.495447e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.495447e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.314709 sec +TOTAL : 3.305181 sec INFO: No Floating Point Exceptions have been reported - 9,491,443,814 cycles # 2.860 GHz - 26,243,392,606 instructions # 2.76 insn per cycle - 3.319931879 seconds time elapsed + 9,752,287,704 cycles # 2.941 GHz + 26,369,462,343 instructions # 2.70 insn per cycle + 3.316567159 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 2386) (avx2: 0) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -136,31 +136,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.sse4_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359218686011 Relative difference = 3.8758807327712803e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.278974e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.566310e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.566310e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.466984e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 4.783441e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 4.783441e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.558625 sec +TOTAL : 2.496548 sec INFO: No Floating Point Exceptions have been reported - 6,762,791,528 cycles # 2.640 GHz - 14,038,966,937 instructions # 2.08 insn per cycle - 2.563817269 seconds time elapsed + 6,902,736,140 cycles # 2.753 GHz + 14,146,955,352 instructions # 2.05 insn per cycle + 2.508688639 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2895) (512y: 0) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -168,31 +168,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.avx2_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 4.605515e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 4.931896e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 4.931896e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 4.747061e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 5.095585e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 5.095585e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 2.383269 sec +TOTAL : 2.355880 sec INFO: No Floating Point Exceptions have been reported - 6,370,579,818 cycles # 2.668 GHz - 13,515,010,631 instructions # 2.12 insn per cycle - 2.388311155 seconds time elapsed + 6,536,932,805 cycles # 2.762 GHz + 13,633,905,312 instructions # 2.09 insn per cycle + 2.367915662 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 2531) (512y: 302) (512z: 0) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -200,31 +200,31 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512y_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08 OK (relative difference <= 5E-3) ========================================================================= -runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= +runExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe -p 2048 256 2 OMP= INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW Process = SIGMA_MSSM_SLHA2_GG_TTX_CPP [gcc 11.3.1] [inlineHel=0] [hardcodePARAM=1] Workflow summary = CPP:MIX+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK FP precision = MIXED (NaN/abnormal=0, zero=0) Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES] -EvtsPerSec[Rmb+ME] (23) = ( 3.438799e+05 ) sec^-1 -EvtsPerSec[MatrixElems] (3) = ( 3.617303e+05 ) sec^-1 -EvtsPerSec[MECalcOnly] (3a) = ( 3.617303e+05 ) sec^-1 +EvtsPerSec[Rmb+ME] (23) = ( 3.589352e+05 ) sec^-1 +EvtsPerSec[MatrixElems] (3) = ( 3.785622e+05 ) sec^-1 +EvtsPerSec[MECalcOnly] (3a) = ( 3.785622e+05 ) sec^-1 MeanMatrixElemValue = ( 2.072848e+00 +- 3.360985e-03 ) GeV^0 -TOTAL : 3.157631 sec +TOTAL : 3.069165 sec INFO: No Floating Point Exceptions have been reported - 5,593,786,532 cycles # 1.770 GHz - 9,209,286,956 instructions # 1.65 insn per cycle - 3.162934960 seconds time elapsed + 5,741,871,289 cycles # 1.864 GHz + 9,325,593,834 instructions # 1.62 insn per cycle + 3.081760977 seconds time elapsed =Symbols in CPPProcess_cpp.o= (~sse4: 0) (avx2: 1456) (512y: 212) (512z: 2059) ------------------------------------------------------------------------- -runTest /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/runTest_cpp.exe +runTest /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/runTest_cpp.exe INFO: The following Floating Point Exceptions will cause SIGFPE program aborts: FE_DIVBYZERO, FE_INVALID, FE_OVERFLOW [ PASSED ] 4 tests. DEBUG: MEK (no multichannel) processed 512 events across 3 channels { no-multichannel : 512 } @@ -232,8 +232,8 @@ INFO: No Floating Point Exceptions have been reported DEBUG: MEK (channelid array) processed 512 events across 3 channels { 1 : 192, 2 : 160, 3 : 160 } INFO: No Floating Point Exceptions have been reported ------------------------------------------------------------------------- -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 -cmpExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/check_cpp.exe --common -p 2 64 2 +cmpExe /data/avalassi/GPU2023/madgraph4gpuBis/epochX/cudacpp/susy_gg_tt.mad/SubProcesses/P1_gg_ttx/build.512z_m_inl0_hrd1/fcheck_cpp.exe 2 64 2 Avg ME (C++/C++) = 2.015836e+00 Avg ME (F77/C++) = 2.0158359178371690 Relative difference = 4.0758688308634e-08