Complete PR 955 for goodhel (resync to master, regenerate code)

.github/workflows/c-cpp.yml

@@ -2,9 +2,9 @@ name: C/C++ CI
 
 on:
   push:
-    branches: [ master ]
+    branches: [ master, master_june24 ]
   pull_request:
-    branches: [ master ]
+    branches: [ master, master_june24 ]
 
 jobs:
   debug_builds:
@@ -38,7 +38,7 @@ jobs:
   CPU_MAC:
     runs-on: macos-latest
     env:
-      FC: gfortran-11
+      FC: gfortran-14 # see #971
     strategy:
       matrix:
         folder: [ epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum, epochX/cudacpp/gg_ttgg.mad/SubProcesses/P1_gg_ttxgg ]

.github/workflows/madgraph_launch_test.yml

@@ -0,0 +1,112 @@
+# WARNING THIS FILE IS AUTOGENERATED -> edit test_simd_madevent.template
+
+
+# This is a basic workflow to help you get started with Actions
+
+name: running acceptance test
+# Controls when the workflow will run
+#    branches: [ main LTS ]
+on:
+  # Triggers the workflow on push or pull request events but only for the 3.4.0 branch
+  push:
+    paths-ignore:
+      - 'docs/**'
+#      - '.github/**'
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+    inputs:
+      message:
+        description: 'running acceptance test'     
+        required: true
+
+env:
+  commitmsg: ${{ github.event.head_commit.message }}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  # This workflow contains a single job called "build"
+
+  simd_cpp_heft_ggh_double:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v2
+        with:
+          submodules: 'true'
+
+      # Runs a set of commands using the runners shell
+      - name: test one of the test testIO_AcceptanceProcOutputIOTests
+        run: |
+            cd $GITHUB_WORKSPACE
+            cd MG5aMC/mg5amcnlo/
+            cp input/.mg5_configuration_default.txt input/mg5_configuration.txt
+            cp Template/LO/Source/.make_opts Template/LO/Source/make_opts
+            ./tests/test_manager.py -p./PLUGIN/CUDACPP_OUTPUT/acceptance_tests/ test_simd_cpp_heft_ggh_double 
+
+  simd_cpp_pptt_mixed:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v2
+        with:
+          submodules: 'true'
+
+      # Runs a set of commands using the runners shell
+      - name: test one of the test testIO_AcceptanceProcOutputIOTests
+        run: |
+            cd $GITHUB_WORKSPACE
+            cd MG5aMC/mg5amcnlo/
+            cp input/.mg5_configuration_default.txt input/mg5_configuration.txt
+            cp Template/LO/Source/.make_opts Template/LO/Source/make_opts
+            ./tests/test_manager.py -p./PLUGIN/CUDACPP_OUTPUT/acceptance_tests/ test_simd_cpp_pptt_mixed 
+
+  simd_cpp_eemumua_float:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v2
+        with:
+          submodules: 'true'
+
+      # Runs a set of commands using the runners shell
+      - name: test one of the test testIO_AcceptanceProcOutputIOTests
+        run: |
+            cd $GITHUB_WORKSPACE
+            cd MG5aMC/mg5amcnlo/
+            cp input/.mg5_configuration_default.txt input/mg5_configuration.txt
+            cp Template/LO/Source/.make_opts Template/LO/Source/make_opts
+            ./tests/test_manager.py -p./PLUGIN/CUDACPP_OUTPUT/acceptance_tests/ test_simd_cpp_eemumua_float 
+
+  simd_cpp_vector_size:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v2
+        with:
+          submodules: 'true'
+
+      # Runs a set of commands using the runners shell
+      - name: test one of the test testIO_AcceptanceProcOutputIOTests
+        run: |
+            cd $GITHUB_WORKSPACE
+            cd MG5aMC/mg5amcnlo/
+            cp input/.mg5_configuration_default.txt input/mg5_configuration.txt
+            cp Template/LO/Source/.make_opts Template/LO/Source/make_opts
+            ./tests/test_manager.py -p./PLUGIN/CUDACPP_OUTPUT/acceptance_tests/ test_simd_cpp_vector_size 

.github/workflows/testsuite_allprocesses.yml

@@ -16,7 +16,7 @@ on:
 
   # Trigger the all-processes workflow for pull requests to master
   pull_request:
-    branches: [ master ]
+    branches: [ master, master_june24 ]
 
   # Trigger the all-processes workflow when new changes to the workflow are pushed
   # (NB: this is now disabled to avoid triggering two jobs when pushing to a branch for which a PR is opened)

.github/workflows/testsuite_oneprocess.sh

@@ -20,9 +20,11 @@ function ECHO() { echo " "; }
 echo "Executing $0 $*"; ECHO
 topdir=$(cd $(dirname $0)/../..; pwd)
 
-# Disable OpenMP in the CI tests
-# To do this, set OMPFLAGS externally to an empty string (#758)
-export OMPFLAGS=
+# Enable OpenMP in the CI tests? (#758)
+###export USEOPENMP=1
+
+# Debug channelid in MatrixElementKernelBase?
+export MG5AMC_CHANNELID_DEBUG=1
 
 # Bypass known issues?
 BYPASS_KNOWN_ISSUES=0 # do not bypass known issues (fail)

.github/workflows/testsuite_oneprocess.yml

@@ -34,8 +34,7 @@ on:
         required: true
         type: choice
         # FIXME? Can the list of supported processes be specified only once in oneprocess.yml or allprocesses.yml?
-        options: [gg_tt.mad, gg_ttg.mad, gg_ttgg.mad, gg_ttggg.mad, ee_mumu.mad, nobm_pp_ttW.mad]
-        ###options: [ee_mumu.mad, gg_tt.mad, gg_ttg.mad, gg_ttgg.mad, gg_ttggg.mad, gg_tt01g.mad, gq_ttq.mad, pp_tt012j.mad]
+        options: [gg_tt.mad, gg_ttg.mad, gg_ttgg.mad, gg_ttggg.mad, ee_mumu.mad, nobm_pp_ttW.mad, susy_gg_tt.mad]
 
 #----------------------------------------------------------------------------------------------------------------------------------
 

epochX/cudacpp/CODEGEN/PLUGIN/CUDACPP_SA_OUTPUT/MG5aMC_patches/PROD/patch.P1

@@ -1,161 +1,3 @@
-diff --git b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/auto_dsig1.f a/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/auto_dsig1.f
-index 4fbb8e6ba..f9e2335de 100644
---- b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/auto_dsig1.f
-+++ a/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/auto_dsig1.f
-@@ -484,23 +484,140 @@ C
-       INTEGER VECSIZE_USED
-
-       INTEGER IVEC
--
--
-+      INTEGER IEXT
-+
-+      INTEGER                    ISUM_HEL
-+      LOGICAL                    MULTI_CHANNEL
-+      COMMON/TO_MATRIX/ISUM_HEL, MULTI_CHANNEL
-+
-+      LOGICAL FIRST_CHID
-+      SAVE FIRST_CHID
-+      DATA FIRST_CHID/.TRUE./
-+      
-+#ifdef MG5AMC_MEEXPORTER_CUDACPP
-+      INCLUDE 'coupl.inc' ! for ALL_G
-+      INCLUDE 'fbridge.inc'
-+      INCLUDE 'fbridge_common.inc'
-+      INCLUDE 'genps.inc'
-+      INCLUDE 'run.inc'
-+      DOUBLE PRECISION OUT2(VECSIZE_MEMMAX)
-+      INTEGER SELECTED_HEL2(VECSIZE_MEMMAX)
-+      INTEGER SELECTED_COL2(VECSIZE_MEMMAX)
-+      DOUBLE PRECISION CBYF1
-+      INTEGER*4 NGOODHEL, NTOTHEL
-+
-+      INTEGER*4 NWARNINGS
-+      SAVE NWARNINGS
-+      DATA NWARNINGS/0/
-+      
-+      LOGICAL FIRST
-+      SAVE FIRST
-+      DATA FIRST/.TRUE./
-+      
-+      IF( FBRIDGE_MODE .LE. 0 ) THEN ! (FortranOnly=0 or BothQuiet=-1 or BothDebug=-2)
-+#endif
-+        call counters_smatrix1multi_start( -1, VECSIZE_USED ) ! fortran=-1
- !$OMP PARALLEL
- !$OMP DO
--      DO IVEC=1, VECSIZE_USED
--        CALL SMATRIX1(P_MULTI(0,1,IVEC),
--     &	                         hel_rand(IVEC),
--     &                           col_rand(IVEC),
--     &				 channel,
--     &                           IVEC,
--     &				 out(IVEC),
--     &				 selected_hel(IVEC),
--     &				 selected_col(IVEC)
--     &				 )
--      ENDDO
-+        DO IVEC=1, VECSIZE_USED
-+          CALL SMATRIX1(P_MULTI(0,1,IVEC),
-+     &      hel_rand(IVEC),
-+     &      col_rand(IVEC),
-+     &      channel,
-+     &      IVEC,
-+     &      out(IVEC),
-+     &      selected_hel(IVEC),
-+     &      selected_col(IVEC)
-+     &      )
-+        ENDDO
- !$OMP END DO
- !$OMP END PARALLEL
-+        call counters_smatrix1multi_stop( -1 ) ! fortran=-1
-+#ifdef MG5AMC_MEEXPORTER_CUDACPP
-+      ENDIF
-+
-+      IF( FBRIDGE_MODE .EQ. 1 .OR. FBRIDGE_MODE .LT. 0 ) THEN ! (CppOnly=1 or BothQuiet=-1 or BothDebug=-2)
-+        IF( LIMHEL.NE.0 ) THEN
-+          WRITE(6,*) 'ERROR! The cudacpp bridge only supports LIMHEL=0'
-+          STOP
-+        ENDIF
-+        IF ( FIRST ) THEN ! exclude first pass (helicity filtering) from timers (#461)
-+          CALL FBRIDGESEQUENCE_NOMULTICHANNEL( FBRIDGE_PBRIDGE, ! multi channel disabled for helicity filtering
-+     &      P_MULTI, ALL_G, HEL_RAND, COL_RAND, OUT2,
-+     &      SELECTED_HEL2, SELECTED_COL2 )
-+          FIRST = .FALSE.
-+c         ! This is a workaround for https://github.com/oliviermattelaer/mg5amc_test/issues/22 (see PR #486)
-+c          IF( FBRIDGE_MODE .EQ. 1 ) THEN ! (CppOnly=1 : SMATRIX1 is not called at all)
-+c            CALL RESET_CUMULATIVE_VARIABLE() ! mimic 'avoid bias of the initialization' within SMATRIX1
-+c          ENDIF
-+          CALL FBRIDGEGETNGOODHEL(FBRIDGE_PBRIDGE,NGOODHEL,NTOTHEL)
-+          IF( NTOTHEL .NE. NCOMB ) THEN
-+            WRITE(6,*) 'ERROR! Cudacpp/Fortran mismatch',
-+     &        ' in total number of helicities', NTOTHEL, NCOMB
-+            STOP
-+          ENDIF
-+          WRITE (6,*) 'NGOODHEL =', NGOODHEL
-+          WRITE (6,*) 'NCOMB =', NCOMB
-+        ENDIF
-+        call counters_smatrix1multi_start( 0, VECSIZE_USED ) ! cudacpp=0
-+        IF ( .NOT. MULTI_CHANNEL ) THEN
-+          CALL FBRIDGESEQUENCE_NOMULTICHANNEL( FBRIDGE_PBRIDGE, ! multi channel disabled
-+     &      P_MULTI, ALL_G, HEL_RAND, COL_RAND, OUT2,
-+     &      SELECTED_HEL2, SELECTED_COL2 )
-+        ELSE
-+          IF( SDE_STRAT.NE.1 ) THEN
-+            WRITE(6,*) 'ERROR! The cudacpp bridge requires SDE=1' ! multi channel single-diagram enhancement strategy
-+            STOP
-+          ENDIF
-+          CALL FBRIDGESEQUENCE(FBRIDGE_PBRIDGE, P_MULTI, ALL_G,
-+     &      HEL_RAND, COL_RAND, CHANNEL, OUT2,
-+     &      SELECTED_HEL2, SELECTED_COL2 ) ! 1-N: multi channel enabled
-+        ENDIF
-+        call counters_smatrix1multi_stop( 0 ) ! cudacpp=0
-+      ENDIF
-+
-+      IF( FBRIDGE_MODE .LT. 0 ) THEN ! (BothQuiet=-1 or BothDebug=-2)
-+        DO IVEC=1, VECSIZE_USED
-+          CBYF1 = OUT2(IVEC)/OUT(IVEC) - 1
-+          FBRIDGE_NCBYF1 = FBRIDGE_NCBYF1 + 1
-+          FBRIDGE_CBYF1SUM = FBRIDGE_CBYF1SUM + CBYF1
-+          FBRIDGE_CBYF1SUM2 = FBRIDGE_CBYF1SUM2 + CBYF1 * CBYF1
-+          IF( CBYF1 .GT. FBRIDGE_CBYF1MAX ) FBRIDGE_CBYF1MAX = CBYF1
-+          IF( CBYF1 .LT. FBRIDGE_CBYF1MIN ) FBRIDGE_CBYF1MIN = CBYF1
-+          IF( FBRIDGE_MODE .EQ. -2 ) THEN ! (BothDebug=-2)
-+            WRITE (*,'(I4,2E16.8,F23.11,I3,I3,I4,I4)')
-+     &        IVEC, OUT(IVEC), OUT2(IVEC), 1+CBYF1,
-+     &        SELECTED_HEL(IVEC), SELECTED_HEL2(IVEC),
-+     &        SELECTED_COL(IVEC), SELECTED_COL2(IVEC)
-+          ENDIF
-+          IF( ABS(CBYF1).GT.5E-5 .AND. NWARNINGS.LT.20 ) THEN
-+            NWARNINGS = NWARNINGS + 1
-+            WRITE (*,'(A,I4,A,I4,2E16.8,F23.11)')
-+     &        'WARNING! (', NWARNINGS, '/20) Deviation more than 5E-5',
-+     &        IVEC, OUT(IVEC), OUT2(IVEC), 1+CBYF1
-+          ENDIF
-+        END DO
-+      ENDIF
-+
-+      IF( FBRIDGE_MODE .EQ. 1 .OR. FBRIDGE_MODE .LT. 0 ) THEN ! (CppOnly=1 or BothQuiet=-1 or BothDebug=-2)
-+        DO IVEC=1, VECSIZE_USED
-+          OUT(IVEC) = OUT2(IVEC) ! use the cudacpp ME instead of the fortran ME!
-+          SELECTED_HEL(IVEC) = SELECTED_HEL2(IVEC) ! use the cudacpp helicity instead of the fortran helicity!
-+          SELECTED_COL(IVEC) = SELECTED_COL2(IVEC) ! use the cudacpp color instead of the fortran color!
-+        END DO
-+      ENDIF
-+#endif
-+
-+      IF ( FIRST_CHID ) THEN
-+        IF ( MULTI_CHANNEL ) THEN
-+          WRITE (*,*) 'MULTI_CHANNEL = TRUE'
-+        ELSE
-+          WRITE (*,*) 'MULTI_CHANNEL = FALSE'
-+        ENDIF
-+        WRITE (*,*) 'CHANNEL_ID =', CHANNEL
-+        FIRST_CHID = .FALSE.
-+      ENDIF
-+
-       RETURN
-       END
-
 diff --git b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/driver.f a/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/driver.f
 index 1124a9164..27a6e4674 100644
 --- b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/driver.f
@@ -284,10 +126,10 @@ index 1124a9164..27a6e4674 100644
        open(unit=lun,file=tempname,status='old',ERR=20)
        fopened=.true.
 diff --git b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/matrix1.f a/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/matrix1.f
-index e73e654d4..27fbe7302 100644
+index 1acba8200..069c74ef4 100644
 --- b/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/matrix1.f
 +++ a/epochX/cudacpp/gg_tt.mad/SubProcesses/P1_gg_ttx/matrix1.f
-@@ -72,7 +72,10 @@ C
+@@ -71,7 +71,10 @@ C
        DATA NB_FAIL /0/
        DOUBLE PRECISION GET_CHANNEL_CUT
        EXTERNAL GET_CHANNEL_CUT
@@ -299,15 +141,7 @@ index e73e654d4..27fbe7302 100644
  C     
  C     This is just to temporarily store the reference grid for
  C      helicity of the DiscreteSampler so as to obtain its number of
-@@ -140,6 +143,7 @@ C     ----------
- C     BEGIN CODE
- C     ----------
-
-+      call counters_smatrix1_start()
-       NTRY(1)=NTRY(1)+1
-       DO I=1,NEXTERNAL
-         JC(I) = +1       
-@@ -217,6 +221,17 @@ C     ----------
+@@ -211,6 +214,17 @@ C     ----------
            ENDIF
            IF(NTRY(1).EQ.MAXTRIES)THEN
              ISHEL=MIN(ISUM_HEL,NGOOD)
@@ -325,22 +159,3 @@ index e73e654d4..27fbe7302 100644
            ENDIF
          ENDIF
        ELSE IF (.NOT.INIT_MODE) THEN  ! random helicity 
-@@ -234,6 +249,7 @@ C       Include the Jacobian from helicity sampling
-         IHEL = HEL_PICKED
-       ELSE
-         ANS = 1D0
-+        call counters_smatrix1_stop()
-         RETURN
-       ENDIF
-       IF (ANS.NE.0D0.AND.(ISUM_HEL .NE. 1.OR.HEL_PICKED.EQ.-1)) THEN
-@@ -278,9 +294,8 @@ C           Set right sign for ANS, based on sign of chosen helicity
-         ENDIF
-       ENDIF
-       ANS=ANS/DBLE(IDEN)
--
-       CALL SELECT_COLOR(RCOL, JAMP2, ICONFIG,1,  ICOL)
--
-+      call counters_smatrix1_stop()
-       END
-
-