diff --git a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512y/output.txt b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512y/output.txt index 7e552dacdd..fb23db52b7 100644 --- a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512y/output.txt +++ b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512y/output.txt @@ -1,91 +1,91 @@ -START: Thu Aug 22 03:55:18 PM CEST 2024 +START: Thu Aug 22 05:08:42 PM CEST 2024 On itgold91.cern.ch [CPU: Intel(R) Xeon(R) Gold 6326 CPU (nproc=32)] [GPU: none]: CUDACPP_RUNTIME_DISABLEFPE is set -CUDACPP_RUNTIME_SKIPXBINCHECKS is not set -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:55 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +CUDACPP_RUNTIME_SKIPXBINCHECKS is set +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:08 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.512y_m_inl0_hrd0/madevent_cpp Now generating 100 events with random seed 21 and granularity 1 ************************************************************ * * @@ -211,1900 +211,1900 @@ __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event starting INFO: need to improve 108 channels __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 19.1611 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 16.9340 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2042s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3223s for 176708 events => throughput is 5.48E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1018s + [COUNTERS] Fortran Other ( 0 ) : 0.0341s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2204s for 176708 events => throughput is 8.02E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0777s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0463s for 16384 events => throughput is 3.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0686s for 176708 events => throughput is 2.57E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0682s for 176708 events => throughput is 2.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7062s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6044s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4235s - [COUNTERS] Fortran Other ( 0 ) : 0.0468s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6080s for 337001 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2219s + [COUNTERS] Fortran Other ( 0 ) : 0.0465s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4073s for 337001 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0216s for 16384 events => throughput is 7.60E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0216s for 16384 events => throughput is 7.58E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0377s for 337001 events => throughput is 8.95E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9238s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7225s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2953s - [COUNTERS] Fortran Other ( 0 ) : 0.0355s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3562s for 196960 events => throughput is 5.53E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1811s + [COUNTERS] Fortran Other ( 0 ) : 0.0352s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2416s for 196960 events => throughput is 8.15E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0670s for 16384 events => throughput is 2.45E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0671s for 16384 events => throughput is 2.44E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1029s for 196960 events => throughput is 1.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7974s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6837s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4741s - [COUNTERS] Fortran Other ( 0 ) : 0.0422s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6277s for 324156 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2877s + [COUNTERS] Fortran Other ( 0 ) : 0.0424s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4363s for 324156 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0381s for 16384 events => throughput is 4.30E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 324156 events => throughput is 5.82E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9751s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5042s for 16384 events => throughput is 3.25E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7835s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5042s for 16384 events => throughput is 3.25E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1537s - [COUNTERS] Fortran Other ( 0 ) : 0.0355s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3054s for 176248 events => throughput is 5.77E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.58E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0498s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2013s for 176248 events => throughput is 8.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.57E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0575s for 176248 events => throughput is 3.07E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6556s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5521s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0746s - [COUNTERS] Fortran Other ( 0 ) : 0.0312s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2495s for 128162 events => throughput is 5.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9990s + [COUNTERS] Fortran Other ( 0 ) : 0.0310s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1736s for 128162 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.57E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0501s for 128162 events => throughput is 2.56E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5765s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0499s for 128162 events => throughput is 2.57E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5012s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G2/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0978s + [COUNTERS] PROGRAM TOTAL : 1.7233s [COUNTERS] Fortran Other ( 0 ) : 0.0675s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2184s for 680231 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0842s for 16384 events => throughput is 1.95E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0240s for 16384 events => throughput is 6.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0482s for 680231 events => throughput is 1.41E+07 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8446s for 680231 events => throughput is 8.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0843s for 16384 events => throughput is 1.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.80E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0483s for 680231 events => throughput is 1.41E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5994s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2257s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2690s - [COUNTERS] Fortran Other ( 0 ) : 0.0409s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3891s for 227876 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.1326s + [COUNTERS] Fortran Other ( 0 ) : 0.0403s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2539s for 227876 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 81920 events => throughput is 1.04E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0333s for 16384 events => throughput is 4.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0733s for 227876 events => throughput is 3.11E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0335s for 16384 events => throughput is 4.90E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 227876 events => throughput is 3.14E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4979s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7711s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4979s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6349s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3135s - [COUNTERS] Fortran Other ( 0 ) : 0.0388s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5011s for 258529 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.78E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1601s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3488s for 258529 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.79E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0382s for 258529 events => throughput is 6.76E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5001s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8134s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5001s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6606s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G75/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4263s - [COUNTERS] Fortran Other ( 0 ) : 0.0439s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5285s for 288195 events => throughput is 5.45E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 81920 events => throughput is 1.03E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0814s for 288195 events => throughput is 3.54E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4992s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9272s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4992s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] PROGRAM TOTAL : 1.2497s + [COUNTERS] Fortran Other ( 0 ) : 0.0432s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3546s for 288195 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0583s for 16384 events => throughput is 2.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0815s for 288195 events => throughput is 3.54E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7498s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6989s - [COUNTERS] Fortran Other ( 0 ) : 0.0493s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6517s for 362045 events => throughput is 5.56E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4852s + [COUNTERS] Fortran Other ( 0 ) : 0.0492s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4377s for 362045 events => throughput is 8.27E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0635s for 16384 events => throughput is 2.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1095s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1705s for 362045 events => throughput is 2.12E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1096s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1704s for 362045 events => throughput is 2.13E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4975s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2015s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4975s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9878s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2152s - [COUNTERS] Fortran Other ( 0 ) : 0.0399s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3353s for 203191 events => throughput is 6.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0846s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2072s for 203191 events => throughput is 9.81E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0773s for 16384 events => throughput is 2.12E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0367s for 16384 events => throughput is 4.46E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0678s for 203191 events => throughput is 3.00E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0368s for 16384 events => throughput is 4.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0671s for 203191 events => throughput is 3.03E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7161s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4992s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5854s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4992s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1335s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3769s for 205739 events => throughput is 5.46E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0277s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2684s for 205739 events => throughput is 7.67E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0057s for 16384 events => throughput is 2.86E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.42E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0058s for 16384 events => throughput is 2.84E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0144s for 205739 events => throughput is 1.43E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6355s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5297s [COUNTERS] OVERALL MEs ( 32 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2660s - [COUNTERS] Fortran Other ( 0 ) : 0.0726s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3663s for 214038 events => throughput is 5.84E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0696s for 49152 events => throughput is 7.06E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 214038 events => throughput is 3.19E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] PROGRAM TOTAL : 1.1092s + [COUNTERS] Fortran Other ( 0 ) : 0.0386s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2403s for 214038 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0816s for 16384 events => throughput is 2.01E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0670s for 214038 events => throughput is 3.19E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7686s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4982s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6110s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4982s for 16384 events => throughput is 3.29E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 4.5654 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 4.0458 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6676s - [COUNTERS] Fortran Other ( 0 ) : 0.0835s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6173s for 344023 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0834s for 81920 events => throughput is 9.83E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0579s for 16384 events => throughput is 2.83E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1013s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1462s for 344023 events => throughput is 2.35E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1684s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] PROGRAM TOTAL : 1.4325s + [COUNTERS] Fortran Other ( 0 ) : 0.0493s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4136s for 344023 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0834s for 81920 events => throughput is 9.82E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0595s for 16384 events => throughput is 2.75E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1014s for 16384 events => throughput is 1.62E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1466s for 344023 events => throughput is 2.35E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9334s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G43/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3916s - [COUNTERS] Fortran Other ( 0 ) : 0.0386s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4113s for 214181 events => throughput is 5.21E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1355s for 212992 events => throughput is 1.57E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0584s for 16384 events => throughput is 2.80E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2681s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2857s for 214181 events => throughput is 7.50E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1356s for 212992 events => throughput is 1.57E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0585s for 16384 events => throughput is 2.80E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0708s for 16384 events => throughput is 2.31E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 214181 events => throughput is 2.16E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0710s for 16384 events => throughput is 2.31E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0995s for 214181 events => throughput is 2.15E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8932s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7692s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4785s - [COUNTERS] Fortran Other ( 0 ) : 0.0419s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0408s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5403s for 279555 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1132s for 147456 events => throughput is 1.30E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0579s for 16384 events => throughput is 2.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3168s + [COUNTERS] Fortran Other ( 0 ) : 0.0424s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3780s for 279555 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1129s for 147456 events => throughput is 1.31E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0617s for 16384 events => throughput is 2.66E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0618s for 16384 events => throughput is 2.65E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0859s for 279555 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9796s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8180s [COUNTERS] OVERALL MEs ( 32 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 2.0882 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 1.6324 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/G67/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0590s - [COUNTERS] Fortran Other ( 0 ) : 0.0753s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2741s for 814370 events => throughput is 6.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.19E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6207s + [COUNTERS] Fortran Other ( 0 ) : 0.0786s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8365s for 814370 events => throughput is 9.74E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0792s for 49152 events => throughput is 6.21E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1108s for 16384 events => throughput is 1.48E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.74E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0327s for 16384 events => throughput is 5.01E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0595s for 814370 events => throughput is 1.37E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0304s for 16384 events => throughput is 5.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0591s for 814370 events => throughput is 1.38E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3467s for 16384 events => throughput is 4.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7123s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3467s for 16384 events => throughput is 4.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3466s for 16384 events => throughput is 4.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2741s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3466s for 16384 events => throughput is 4.73E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 11.1157 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 9.9266 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1462s - [COUNTERS] Fortran Other ( 0 ) : 0.0813s + [COUNTERS] PROGRAM TOTAL : 2.6455s + [COUNTERS] Fortran Other ( 0 ) : 0.0811s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5478s for 933480 events => throughput is 6.03E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1015s for 16384 events => throughput is 1.61E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1003s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1595s for 933480 events => throughput is 5.85E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0460s for 933480 events => throughput is 8.92E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 49152 events => throughput is 6.33E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1035s for 16384 events => throughput is 1.58E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1002s for 16384 events => throughput is 1.64E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1592s for 933480 events => throughput is 5.86E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.9985s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1477s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6470s [COUNTERS] OVERALL MEs ( 32 ) : 0.9985s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8965s - [COUNTERS] Fortran Other ( 0 ) : 0.0355s + [COUNTERS] PROGRAM TOTAL : 1.7616s + [COUNTERS] Fortran Other ( 0 ) : 0.0360s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4255s for 226350 events => throughput is 5.32E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0766s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1221s for 226350 events => throughput is 1.85E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2913s for 226350 events => throughput is 7.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0773s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0799s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1217s for 226350 events => throughput is 1.86E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9991s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8973s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9991s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9978s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7638s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9978s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0550s - [COUNTERS] Fortran Other ( 0 ) : 0.0419s + [COUNTERS] PROGRAM TOTAL : 1.8629s + [COUNTERS] Fortran Other ( 0 ) : 0.0411s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6512s for 323984 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0503s for 16384 events => throughput is 3.26E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4592s for 323984 events => throughput is 7.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0511s for 16384 events => throughput is 3.21E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0633s for 16384 events => throughput is 2.59E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0934s for 323984 events => throughput is 3.47E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0931s for 323984 events => throughput is 3.48E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s [COUNTERS] CudaCpp MEs ( 19 ) : 0.9979s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0571s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8650s [COUNTERS] OVERALL MEs ( 32 ) : 0.9979s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1164s - [COUNTERS] Fortran Other ( 0 ) : 0.0425s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7128s for 355559 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0501s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0622s for 16384 events => throughput is 2.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0934s for 355559 events => throughput is 3.81E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9100s + [COUNTERS] Fortran Other ( 0 ) : 0.0422s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5040s for 355559 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0513s for 16384 events => throughput is 3.19E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0622s for 16384 events => throughput is 2.64E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0929s for 355559 events => throughput is 3.83E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9980s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1184s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9980s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9987s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9113s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9987s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G92/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8575s - [COUNTERS] Fortran Other ( 0 ) : 0.0409s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0441s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4560s for 255849 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.7028s + [COUNTERS] Fortran Other ( 0 ) : 0.0402s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3042s for 255849 events => throughput is 8.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0386s for 16384 events => throughput is 4.25E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0843s for 255849 events => throughput is 3.03E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0836s for 255849 events => throughput is 3.06E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9995s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8581s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9995s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9984s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7044s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9984s for 16384 events => throughput is 1.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 10.9818 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 9.3128 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9072s - [COUNTERS] Fortran Other ( 0 ) : 0.0778s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4099s for 859290 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1077s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.4562s + [COUNTERS] Fortran Other ( 0 ) : 0.0771s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9586s for 859290 events => throughput is 8.96E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1067s for 16384 events => throughput is 1.54E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0576s for 16384 events => throughput is 2.84E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0980s for 859290 events => throughput is 8.77E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0992s for 859290 events => throughput is 8.66E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0012s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9060s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0012s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4553s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1753s - [COUNTERS] Fortran Other ( 0 ) : 0.0927s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.7908s for 1098402 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0756s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.6111s + [COUNTERS] Fortran Other ( 0 ) : 0.0920s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0426s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2276s for 1098402 events => throughput is 8.95E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0124s for 16384 events => throughput is 1.32E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.55E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0429s for 1098402 events => throughput is 2.56E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0010s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1742s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0010s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6107s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1419s - [COUNTERS] Fortran Other ( 0 ) : 0.0443s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7465s for 378380 events => throughput is 5.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0537s for 16384 events => throughput is 3.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.92E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0849s for 378380 events => throughput is 4.46E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9287s + [COUNTERS] Fortran Other ( 0 ) : 0.0445s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5309s for 378380 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0845s for 378380 events => throughput is 4.48E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 1.0008s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1410s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9279s [COUNTERS] OVERALL MEs ( 32 ) : 1.0008s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G65/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7207s - [COUNTERS] Fortran Other ( 0 ) : 0.0731s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3613s for 819579 events => throughput is 6.02E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0816s for 16384 events => throughput is 2.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0144s for 16384 events => throughput is 1.14E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0391s for 819579 events => throughput is 2.10E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.2806s + [COUNTERS] Fortran Other ( 0 ) : 0.0723s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9229s for 819579 events => throughput is 8.88E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0812s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0145s for 16384 events => throughput is 1.13E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0389s for 819579 events => throughput is 2.11E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0038s for 16384 events => throughput is 1.63E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7170s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0038s for 16384 events => throughput is 1.63E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0027s for 16384 events => throughput is 1.63E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2779s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0027s for 16384 events => throughput is 1.63E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.4489 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.2459 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4381s - [COUNTERS] Fortran Other ( 0 ) : 0.0437s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6473s for 330261 events => throughput is 5.10E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2357s + [COUNTERS] Fortran Other ( 0 ) : 0.0438s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4443s for 330261 events => throughput is 7.43E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0867s for 81920 events => throughput is 9.45E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0559s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0566s for 16384 events => throughput is 2.90E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0074s for 16384 events => throughput is 2.23E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0198s for 330261 events => throughput is 1.67E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0074s for 16384 events => throughput is 2.22E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0196s for 330261 events => throughput is 1.68E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9397s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7373s [COUNTERS] OVERALL MEs ( 32 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 2.2846 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 1.7858 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2742s - [COUNTERS] Fortran Other ( 0 ) : 0.0832s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4380s for 919173 events => throughput is 6.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0838s for 16384 events => throughput is 1.96E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1318s for 919173 events => throughput is 6.97E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] PROGRAM TOTAL : 1.7753s + [COUNTERS] Fortran Other ( 0 ) : 0.0826s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9398s for 919173 events => throughput is 9.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.73E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0836s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1313s for 919173 events => throughput is 7.00E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3120s for 16384 events => throughput is 5.25E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9622s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3120s for 16384 events => throughput is 5.25E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3121s for 16384 events => throughput is 5.25E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4631s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3121s for 16384 events => throughput is 5.25E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 13.5963 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 11.1734 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1762s - [COUNTERS] Fortran Other ( 0 ) : 0.0318s + [COUNTERS] PROGRAM TOTAL : 1.0910s + [COUNTERS] Fortran Other ( 0 ) : 0.0317s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2788s for 142763 events => throughput is 5.12E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.98E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1932s for 142763 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0899s for 142763 events => throughput is 1.59E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0898s for 142763 events => throughput is 1.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5004s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6758s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5906s [COUNTERS] OVERALL MEs ( 32 ) : 0.5004s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9844s - [COUNTERS] Fortran Other ( 0 ) : 0.0973s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8424s for 1119813 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1090s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.3808s + [COUNTERS] Fortran Other ( 0 ) : 0.0964s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2405s for 1119813 events => throughput is 9.03E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1092s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1077s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1710s for 1119813 events => throughput is 6.55E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1704s for 1119813 events => throughput is 6.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5007s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4838s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8801s [COUNTERS] OVERALL MEs ( 32 ) : 0.5007s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1555s - [COUNTERS] Fortran Other ( 0 ) : 0.1090s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2300s for 1357398 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0870s for 16384 events => throughput is 1.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.47E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0556s for 1357398 events => throughput is 2.44E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.4115s + [COUNTERS] Fortran Other ( 0 ) : 0.1083s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4875s for 1357398 events => throughput is 9.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0868s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0554s for 1357398 events => throughput is 2.45E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6550s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9112s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7504s - [COUNTERS] Fortran Other ( 0 ) : 0.0517s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7157s for 398526 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0563s for 16384 events => throughput is 2.91E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1142s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1647s for 398526 events => throughput is 2.42E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.5121s + [COUNTERS] Fortran Other ( 0 ) : 0.0512s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4786s for 398526 events => throughput is 8.33E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1140s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1645s for 398526 events => throughput is 2.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5006s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2498s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5006s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0118s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G53/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1018s - [COUNTERS] Fortran Other ( 0 ) : 0.0903s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9630s for 1103762 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0767s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0860s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1221s for 16384 events => throughput is 1.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1832s for 1103762 events => throughput is 6.02E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 2.5099s + [COUNTERS] Fortran Other ( 0 ) : 0.0898s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3733s for 1103762 events => throughput is 8.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0769s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0858s for 16384 events => throughput is 1.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1204s for 16384 events => throughput is 1.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1836s for 1103762 events => throughput is 6.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6013s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0096s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3767s - [COUNTERS] Fortran Other ( 0 ) : 0.0444s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4661s for 272273 events => throughput is 5.84E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0582s for 16384 events => throughput is 2.81E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0528s for 16384 events => throughput is 3.10E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2165s + [COUNTERS] Fortran Other ( 0 ) : 0.0440s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3056s for 272273 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0585s for 16384 events => throughput is 2.80E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1093s for 272273 events => throughput is 2.49E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4986s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8781s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4986s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7181s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4984s for 16384 events => throughput is 3.29E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 1.2276 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 1.1616 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/G71/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2169s + [COUNTERS] PROGRAM TOTAL : 1.1512s [COUNTERS] Fortran Other ( 0 ) : 0.0285s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2208s for 109714 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0820s for 49152 events => throughput is 5.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0166s for 16384 events => throughput is 9.87E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1558s for 109714 events => throughput is 7.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0815s for 49152 events => throughput is 6.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.89E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0167s for 16384 events => throughput is 9.82E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.39E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7093s for 16384 events => throughput is 2.31E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5075s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7093s for 16384 events => throughput is 2.31E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7090s for 16384 events => throughput is 2.31E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4423s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7090s for 16384 events => throughput is 2.31E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.1412 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 1.6305 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1307s - [COUNTERS] Fortran Other ( 0 ) : 0.0868s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4806s for 949349 events => throughput is 6.41E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6195s + [COUNTERS] Fortran Other ( 0 ) : 0.0855s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9722s for 949349 events => throughput is 9.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0656s for 16384 events => throughput is 2.50E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1092s for 949349 events => throughput is 8.69E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0646s for 16384 events => throughput is 2.54E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1079s for 949349 events => throughput is 8.80E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9776s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4664s [COUNTERS] OVERALL MEs ( 32 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 5.9927 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 5.4768 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7619s - [COUNTERS] Fortran Other ( 0 ) : 0.0352s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3387s for 181152 events => throughput is 5.35E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6656s + [COUNTERS] Fortran Other ( 0 ) : 0.0351s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2359s for 181152 events => throughput is 7.68E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0845s for 16384 events => throughput is 1.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0590s for 16384 events => throughput is 2.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0903s for 181152 events => throughput is 2.01E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0902s for 181152 events => throughput is 2.01E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 1.0030s for 16384 events => throughput is 1.63E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7589s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6627s [COUNTERS] OVERALL MEs ( 32 ) : 1.0030s for 16384 events => throughput is 1.63E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9990s - [COUNTERS] Fortran Other ( 0 ) : 0.0418s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5887s for 293756 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0522s for 16384 events => throughput is 3.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0665s for 16384 events => throughput is 2.46E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0926s for 293756 events => throughput is 3.17E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.8280s + [COUNTERS] Fortran Other ( 0 ) : 0.0417s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4157s for 293756 events => throughput is 7.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0788s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0519s for 16384 events => throughput is 3.16E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0657s for 16384 events => throughput is 2.49E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0942s for 293756 events => throughput is 3.12E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9987s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0004s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8277s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0004s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2048s - [COUNTERS] Fortran Other ( 0 ) : 0.0516s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7675s for 405834 events => throughput is 5.29E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0743s for 16384 events => throughput is 2.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1094s for 405834 events => throughput is 3.71E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.9552s + [COUNTERS] Fortran Other ( 0 ) : 0.0524s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5170s for 405834 events => throughput is 7.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0742s for 16384 events => throughput is 2.21E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1086s for 405834 events => throughput is 3.74E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2042s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9543s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 18.2135 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 16.0514 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9496s - [COUNTERS] Fortran Other ( 0 ) : 0.0767s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4120s for 847188 events => throughput is 6.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1035s for 16384 events => throughput is 1.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1226s for 847188 events => throughput is 6.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9489s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] PROGRAM TOTAL : 2.4995s + [COUNTERS] Fortran Other ( 0 ) : 0.0765s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9624s for 847188 events => throughput is 8.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1031s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1225s for 847188 events => throughput is 6.92E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4986s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6895s + [COUNTERS] PROGRAM TOTAL : 1.5937s [COUNTERS] Fortran Other ( 0 ) : 0.0330s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3140s for 167274 events => throughput is 5.33E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2187s for 167274 events => throughput is 7.65E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0448s for 16384 events => throughput is 3.66E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0636s for 167274 events => throughput is 2.63E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0635s for 167274 events => throughput is 2.63E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6909s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9988s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5949s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9988s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3076s - [COUNTERS] Fortran Other ( 0 ) : 0.0976s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8893s for 1150245 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0257s for 16384 events => throughput is 6.38E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0605s for 1150245 events => throughput is 1.90E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.6975s + [COUNTERS] Fortran Other ( 0 ) : 0.0970s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2803s for 1150245 events => throughput is 8.98E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0256s for 16384 events => throughput is 6.40E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0597s for 1150245 events => throughput is 1.93E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0010s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3066s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0010s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6968s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0007s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9939s - [COUNTERS] Fortran Other ( 0 ) : 0.0477s + [COUNTERS] PROGRAM TOTAL : 1.7945s + [COUNTERS] Fortran Other ( 0 ) : 0.0470s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6589s for 355348 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0296s for 16384 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 355348 events => throughput is 7.42E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4574s for 355348 events => throughput is 7.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0297s for 16384 events => throughput is 5.51E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 355348 events => throughput is 7.41E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9930s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0009s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0019s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7927s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0019s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9733s - [COUNTERS] Fortran Other ( 0 ) : 0.0787s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0408s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4191s for 864266 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1063s for 16384 events => throughput is 1.54E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1283s for 864266 events => throughput is 6.74E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 2.5127s + [COUNTERS] Fortran Other ( 0 ) : 0.0782s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9669s for 864266 events => throughput is 8.94E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1069s for 16384 events => throughput is 1.53E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1279s for 864266 events => throughput is 6.76E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0066s for 16384 events => throughput is 1.63E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9666s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0066s for 16384 events => throughput is 1.63E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5142s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9545s - [COUNTERS] Fortran Other ( 0 ) : 0.0400s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5670s for 285525 events => throughput is 5.04E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.7885s + [COUNTERS] Fortran Other ( 0 ) : 0.0399s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4012s for 285525 events => throughput is 7.12E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0586s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0804s for 285525 events => throughput is 3.55E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0585s for 16384 events => throughput is 2.80E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0802s for 285525 events => throughput is 3.56E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9559s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7899s [COUNTERS] OVERALL MEs ( 32 ) : 0.9986s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6889s - [COUNTERS] Fortran Other ( 0 ) : 0.0375s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3392s for 189666 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0809s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5782s + [COUNTERS] Fortran Other ( 0 ) : 0.0369s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2293s for 189666 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0808s for 16384 events => throughput is 2.03E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0299s for 16384 events => throughput is 5.48E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0300s for 16384 events => throughput is 5.46E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0533s for 189666 events => throughput is 3.56E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0008s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6880s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0008s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0002s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5780s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0002s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5887s - [COUNTERS] Fortran Other ( 0 ) : 0.0306s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2487s for 124553 events => throughput is 5.01E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0587s for 124553 events => throughput is 2.12E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.5162s + [COUNTERS] Fortran Other ( 0 ) : 0.0301s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1756s for 124553 events => throughput is 7.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0549s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0425s for 16384 events => throughput is 3.85E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0589s for 124553 events => throughput is 2.11E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9987s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5900s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9987s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9988s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5174s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9988s for 16384 events => throughput is 1.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 3.1264 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 2.7359 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G48/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5440s - [COUNTERS] Fortran Other ( 0 ) : 0.0442s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0408s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5752s for 318589 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 49152 events => throughput is 6.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0878s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1292s for 318589 events => throughput is 2.47E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.3546s + [COUNTERS] Fortran Other ( 0 ) : 0.0441s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3850s for 318589 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0537s for 16384 events => throughput is 3.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0874s for 16384 events => throughput is 1.87E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1288s for 318589 events => throughput is 2.47E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4979s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0461s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4979s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4983s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8563s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4983s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5632s - [COUNTERS] Fortran Other ( 0 ) : 0.0436s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6643s for 343552 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0517s for 16384 events => throughput is 3.17E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3619s + [COUNTERS] Fortran Other ( 0 ) : 0.0435s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4629s for 343552 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0518s for 16384 events => throughput is 3.16E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0605s for 16384 events => throughput is 2.71E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0606s for 16384 events => throughput is 2.70E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0878s for 343552 events => throughput is 3.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0651s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8638s [COUNTERS] OVERALL MEs ( 32 ) : 0.4981s for 16384 events => throughput is 3.29E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 10.7650 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 9.2561 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3502s - [COUNTERS] Fortran Other ( 0 ) : 0.0354s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3995s for 223142 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0684s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1096s for 223142 events => throughput is 2.04E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2229s + [COUNTERS] Fortran Other ( 0 ) : 0.0353s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2723s for 223142 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0685s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1098s for 223142 events => throughput is 2.03E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8505s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7229s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5211s - [COUNTERS] Fortran Other ( 0 ) : 0.0424s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6218s for 323723 events => throughput is 5.21E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0600s for 16384 events => throughput is 2.73E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3392s + [COUNTERS] Fortran Other ( 0 ) : 0.0417s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4353s for 323723 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0601s for 16384 events => throughput is 2.73E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0863s for 323723 events => throughput is 3.75E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4993s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0218s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4993s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5034s for 16384 events => throughput is 3.25E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8357s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5034s for 16384 events => throughput is 3.25E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3950s - [COUNTERS] Fortran Other ( 0 ) : 0.0372s + [COUNTERS] PROGRAM TOTAL : 1.2558s + [COUNTERS] Fortran Other ( 0 ) : 0.0373s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4359s for 243889 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0792s for 49152 events => throughput is 6.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0739s for 16384 events => throughput is 2.22E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 243889 events => throughput is 2.24E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2976s for 243889 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0742s for 16384 events => throughput is 2.21E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1091s for 243889 events => throughput is 2.24E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8951s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7555s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5003s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4895s - [COUNTERS] Fortran Other ( 0 ) : 0.0410s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6167s for 320856 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 49152 events => throughput is 6.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0492s for 16384 events => throughput is 3.33E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3081s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4326s for 320856 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0797s for 49152 events => throughput is 6.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0528s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0491s for 16384 events => throughput is 3.33E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 320856 events => throughput is 4.42E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9899s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8085s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G34/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2154s - [COUNTERS] Fortran Other ( 0 ) : 0.0993s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2245s for 1259120 events => throughput is 5.66E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0866s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.5701s + [COUNTERS] Fortran Other ( 0 ) : 0.0988s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5807s for 1259120 events => throughput is 7.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 49152 events => throughput is 6.33E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0869s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0504s for 16384 events => throughput is 3.25E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0966s for 1259120 events => throughput is 1.30E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0961s for 1259120 events => throughput is 1.31E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.7158s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0706s [COUNTERS] OVERALL MEs ( 32 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7405s - [COUNTERS] Fortran Other ( 0 ) : 0.0503s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7213s for 403861 events => throughput is 5.60E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5075s + [COUNTERS] Fortran Other ( 0 ) : 0.0502s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4883s for 403861 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1070s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1513s for 403861 events => throughput is 2.67E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1517s for 403861 events => throughput is 2.66E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5000s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2406s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5000s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0076s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 1.9843 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 1.6676 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0173s - [COUNTERS] Fortran Other ( 0 ) : 0.0421s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5521s for 285337 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0832s for 81920 events => throughput is 9.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8525s + [COUNTERS] Fortran Other ( 0 ) : 0.0412s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3868s for 285337 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0832s for 81920 events => throughput is 9.85E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0415s for 16384 events => throughput is 3.95E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0259s for 16384 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0413s for 285337 events => throughput is 6.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0033s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0266s for 16384 events => throughput is 6.16E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0420s for 285337 events => throughput is 6.79E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1529s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8644s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1529s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1527s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6998s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1527s for 16384 events => throughput is 1.07E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G46/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9485s - [COUNTERS] Fortran Other ( 0 ) : 0.0412s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4729s for 258650 events => throughput is 5.47E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0426s for 16384 events => throughput is 3.84E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7964s + [COUNTERS] Fortran Other ( 0 ) : 0.0410s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3197s for 258650 events => throughput is 8.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0427s for 16384 events => throughput is 3.84E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0378s for 16384 events => throughput is 4.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 258650 events => throughput is 4.82E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0536s for 258650 events => throughput is 4.82E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1528s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7957s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1528s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6433s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 2.3862 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 1.9083 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G25/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5549s - [COUNTERS] Fortran Other ( 0 ) : 0.0681s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0981s for 669977 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1925s + [COUNTERS] Fortran Other ( 0 ) : 0.0673s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7355s for 669977 events => throughput is 9.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0630s for 16384 events => throughput is 2.60E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0031s for 16384 events => throughput is 5.30E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0221s for 669977 events => throughput is 3.03E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 5.04E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0216s for 669977 events => throughput is 3.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4019s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0381s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8130s - [COUNTERS] Fortran Other ( 0 ) : 0.0349s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3693s for 205420 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0681s for 16384 events => throughput is 2.41E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0151s for 16384 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.97E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.6968s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2514s for 205420 events => throughput is 8.17E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0678s for 16384 events => throughput is 2.42E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0354s for 16384 events => throughput is 4.63E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0152s for 16384 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0257s for 205420 events => throughput is 7.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1528s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6602s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1528s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5438s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 9.2377 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 8.2780 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3475s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3903s for 218285 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0772s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2229s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2644s for 218285 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0772s for 16384 events => throughput is 2.12E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0721s for 16384 events => throughput is 2.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1164s for 218285 events => throughput is 1.88E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1162s for 218285 events => throughput is 1.88E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8487s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7240s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4117s - [COUNTERS] Fortran Other ( 0 ) : 0.0438s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5705s for 318651 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0535s for 318651 events => throughput is 5.96E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2240s + [COUNTERS] Fortran Other ( 0 ) : 0.0437s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3829s for 318651 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0360s for 16384 events => throughput is 4.55E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0535s for 318651 events => throughput is 5.95E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9129s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4985s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7255s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4985s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1898s - [COUNTERS] Fortran Other ( 0 ) : 0.0326s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2979s for 164085 events => throughput is 5.51E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0775s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0972s + [COUNTERS] Fortran Other ( 0 ) : 0.0329s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2036s for 164085 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0514s for 16384 events => throughput is 3.19E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0723s for 164085 events => throughput is 2.27E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5009s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6889s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5963s [COUNTERS] OVERALL MEs ( 32 ) : 0.5009s for 16384 events => throughput is 3.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1834s - [COUNTERS] Fortran Other ( 0 ) : 0.0333s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3423s for 177884 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0540s for 16384 events => throughput is 3.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 4.00E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0571s for 177884 events => throughput is 3.11E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] PROGRAM TOTAL : 1.0817s + [COUNTERS] Fortran Other ( 0 ) : 0.0336s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2396s for 177884 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0773s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 3.99E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0572s for 177884 events => throughput is 3.11E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6845s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5829s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4988s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1432s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3763s for 206659 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0219s + [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2549s for 206659 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0094s for 16384 events => throughput is 1.74E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0096s for 16384 events => throughput is 1.71E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.09E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6443s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4989s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5223s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1911s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3338s for 195643 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0750s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2194s for 195643 events => throughput is 8.92E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0325s for 16384 events => throughput is 5.04E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0603s for 195643 events => throughput is 3.24E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 195643 events => throughput is 3.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4987s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6925s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5763s [COUNTERS] OVERALL MEs ( 32 ) : 0.4987s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7122s - [COUNTERS] Fortran Other ( 0 ) : 0.0477s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6626s for 370750 events => throughput is 5.60E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4965s + [COUNTERS] Fortran Other ( 0 ) : 0.0480s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4451s for 370750 events => throughput is 8.33E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1146s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1773s for 370750 events => throughput is 2.09E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0542s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1138s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1769s for 370750 events => throughput is 2.10E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5007s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2115s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5007s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5009s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9956s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5009s for 16384 events => throughput is 3.27E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.1425 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 1.6264 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/G42/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1319s - [COUNTERS] Fortran Other ( 0 ) : 0.0890s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5114s for 974583 events => throughput is 6.45E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6164s + [COUNTERS] Fortran Other ( 0 ) : 0.0885s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9970s for 974583 events => throughput is 9.78E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0941s for 974583 events => throughput is 1.04E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0782s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0937s for 974583 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1532s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9787s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1532s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4635s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1530s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 27.4712 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 22.8393 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3650s - [COUNTERS] Fortran Other ( 0 ) : 0.0771s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4165s for 850849 events => throughput is 6.01E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1097s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0377s for 16384 events => throughput is 4.35E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0684s for 850849 events => throughput is 1.24E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.9114s + [COUNTERS] Fortran Other ( 0 ) : 0.0772s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9641s for 850849 events => throughput is 8.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1110s for 16384 events => throughput is 1.48E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0369s for 16384 events => throughput is 4.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0671s for 850849 events => throughput is 1.27E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5000s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8650s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5000s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4116s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2885s - [COUNTERS] Fortran Other ( 0 ) : 0.0722s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3897s for 778343 events => throughput is 5.60E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0888s for 16384 events => throughput is 1.85E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0286s for 16384 events => throughput is 5.72E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0547s for 778343 events => throughput is 1.42E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.8590s + [COUNTERS] Fortran Other ( 0 ) : 0.0717s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9598s for 778343 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0754s for 81920 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0890s for 16384 events => throughput is 1.84E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0287s for 16384 events => throughput is 5.71E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0551s for 778343 events => throughput is 1.41E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7888s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3595s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.8626s - [COUNTERS] Fortran Other ( 0 ) : 0.1006s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9654s for 1190413 events => throughput is 6.06E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0108s for 16384 events => throughput is 1.52E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0443s for 1190413 events => throughput is 2.69E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.2061s + [COUNTERS] Fortran Other ( 0 ) : 0.0996s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3103s for 1190413 events => throughput is 9.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0863s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0107s for 16384 events => throughput is 1.53E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0442s for 1190413 events => throughput is 2.69E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3630s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4993s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7069s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4993s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4223s - [COUNTERS] Fortran Other ( 0 ) : 0.0451s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5652s for 314106 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0409s for 16384 events => throughput is 4.01E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0619s for 314106 events => throughput is 5.07E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] PROGRAM TOTAL : 1.2367s + [COUNTERS] Fortran Other ( 0 ) : 0.0448s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3799s for 314106 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0403s for 16384 events => throughput is 4.06E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0617s for 314106 events => throughput is 5.09E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9229s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4995s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4994s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7373s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4994s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5031s - [COUNTERS] Fortran Other ( 0 ) : 0.0817s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4508s for 882930 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1092s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0782s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1277s for 882930 events => throughput is 6.91E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.0370s + [COUNTERS] Fortran Other ( 0 ) : 0.0815s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9849s for 882930 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1086s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0782s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1279s for 882930 events => throughput is 6.90E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0035s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4996s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5372s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2616s - [COUNTERS] Fortran Other ( 0 ) : 0.0343s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3376s for 187611 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.1517s + [COUNTERS] Fortran Other ( 0 ) : 0.0352s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2281s for 187611 events => throughput is 8.22E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0609s for 16384 events => throughput is 2.69E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0952s for 187611 events => throughput is 1.97E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0608s for 16384 events => throughput is 2.69E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0948s for 187611 events => throughput is 1.98E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7636s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6543s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4974s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8801s - [COUNTERS] Fortran Other ( 0 ) : 0.1365s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.7805s for 1696178 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0875s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0841s for 16384 events => throughput is 1.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1456s for 1696178 events => throughput is 1.17E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.9693s + [COUNTERS] Fortran Other ( 0 ) : 0.1354s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8735s for 1696178 events => throughput is 9.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0879s for 16384 events => throughput is 1.86E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0827s for 16384 events => throughput is 1.98E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1429s for 1696178 events => throughput is 1.19E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 3.3824s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4713s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1384s - [COUNTERS] Fortran Other ( 0 ) : 0.0309s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2683s for 138227 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0563s for 16384 events => throughput is 2.91E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0541s for 16384 events => throughput is 3.03E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0752s for 138227 events => throughput is 1.84E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0554s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1865s for 138227 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0748s for 138227 events => throughput is 1.85E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4983s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6401s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4983s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5574s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4980s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2421s + [COUNTERS] PROGRAM TOTAL : 1.1097s [COUNTERS] Fortran Other ( 0 ) : 0.0395s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3691s for 215899 events => throughput is 5.85E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0768s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0803s for 16384 events => throughput is 2.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0302s for 16384 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0663s for 215899 events => throughput is 3.26E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2394s for 215899 events => throughput is 9.02E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0301s for 16384 events => throughput is 5.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0664s for 215899 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7416s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5005s for 16384 events => throughput is 3.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6100s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4997s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2964s - [COUNTERS] Fortran Other ( 0 ) : 0.0394s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4908s for 254421 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0556s for 16384 events => throughput is 2.95E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.86E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0341s for 254421 events => throughput is 7.46E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.1437s + [COUNTERS] Fortran Other ( 0 ) : 0.0390s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3415s for 254421 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0540s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.89E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0340s for 254421 events => throughput is 7.48E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5002s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7963s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5002s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4994s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6443s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4994s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.8664s - [COUNTERS] Fortran Other ( 0 ) : 0.0872s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8268s for 1024423 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1332s for 1024423 events => throughput is 7.69E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 2.3002s + [COUNTERS] Fortran Other ( 0 ) : 0.0861s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2632s for 1024423 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0862s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1326s for 1024423 events => throughput is 7.72E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4975s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3688s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4975s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4976s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8026s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4976s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2043s - [COUNTERS] Fortran Other ( 0 ) : 0.0374s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3336s for 193396 events => throughput is 5.80E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0948s for 16384 events => throughput is 1.73E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 193396 events => throughput is 3.22E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 1.0887s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2183s for 193396 events => throughput is 8.86E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0945s for 16384 events => throughput is 1.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0316s for 16384 events => throughput is 5.18E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0599s for 193396 events => throughput is 3.23E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7045s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4998s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5888s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4999s for 16384 events => throughput is 3.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6496s - [COUNTERS] Fortran Other ( 0 ) : 0.0490s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6515s for 362054 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.98E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0961s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1452s for 362054 events => throughput is 2.49E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.4357s + [COUNTERS] Fortran Other ( 0 ) : 0.0487s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4368s for 362054 events => throughput is 8.29E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0961s for 16384 events => throughput is 1.70E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1459s for 362054 events => throughput is 2.48E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1519s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4977s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9378s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4978s for 16384 events => throughput is 3.29E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G76/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3722s - [COUNTERS] Fortran Other ( 0 ) : 0.0452s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4553s for 265638 events => throughput is 5.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0502s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0888s for 265638 events => throughput is 2.99E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 1.2154s + [COUNTERS] Fortran Other ( 0 ) : 0.0451s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3005s for 265638 events => throughput is 8.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0763s for 16384 events => throughput is 2.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0501s for 16384 events => throughput is 3.27E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0887s for 265638 events => throughput is 2.99E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8731s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4991s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7165s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4990s for 16384 events => throughput is 3.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.1285 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 0.9722 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1179s - [COUNTERS] Fortran Other ( 0 ) : 0.0407s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4925s for 259134 events => throughput is 5.26E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9615s + [COUNTERS] Fortran Other ( 0 ) : 0.0406s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3369s for 259134 events => throughput is 7.69E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0430s for 16384 events => throughput is 3.81E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0319s for 16384 events => throughput is 5.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0426s for 16384 events => throughput is 3.85E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0318s for 16384 events => throughput is 5.14E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 259134 events => throughput is 5.41E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3146s for 16384 events => throughput is 5.21E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8033s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3146s for 16384 events => throughput is 5.21E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3145s for 16384 events => throughput is 5.21E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6469s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3145s for 16384 events => throughput is 5.21E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 3.1665 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 2.7242 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7748s - [COUNTERS] Fortran Other ( 0 ) : 0.0344s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3397s for 187490 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0732s for 16384 events => throughput is 2.24E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.09E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0167s for 187490 events => throughput is 1.13E+07 events/s + [COUNTERS] PROGRAM TOTAL : 0.6585s + [COUNTERS] Fortran Other ( 0 ) : 0.0343s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2288s for 187490 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0673s for 16384 events => throughput is 2.43E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.10E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0166s for 187490 events => throughput is 1.13E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1540s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6208s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1540s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5042s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8467s - [COUNTERS] Fortran Other ( 0 ) : 0.0398s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0408s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4125s for 229909 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0179s for 16384 events => throughput is 9.14E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0303s for 229909 events => throughput is 7.58E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7128s + [COUNTERS] Fortran Other ( 0 ) : 0.0397s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2777s for 229909 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0441s for 16384 events => throughput is 3.72E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0179s for 16384 events => throughput is 9.13E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0302s for 229909 events => throughput is 7.62E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1544s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6923s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1544s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1545s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5583s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1545s for 16384 events => throughput is 1.06E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7690s - [COUNTERS] Fortran Other ( 0 ) : 0.0334s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3282s for 170163 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0453s for 16384 events => throughput is 3.62E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0238s for 16384 events => throughput is 6.89E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0354s for 170163 events => throughput is 4.81E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 0.6669s + [COUNTERS] Fortran Other ( 0 ) : 0.0332s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2260s for 170163 events => throughput is 7.53E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0456s for 16384 events => throughput is 3.60E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0237s for 16384 events => throughput is 6.92E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0353s for 170163 events => throughput is 4.82E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1538s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6152s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5131s [COUNTERS] OVERALL MEs ( 32 ) : 0.1538s for 16384 events => throughput is 1.07E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7405s + [COUNTERS] PROGRAM TOTAL : 0.6501s [COUNTERS] Fortran Other ( 0 ) : 0.0324s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2836s for 155440 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0696s for 16384 events => throughput is 2.35E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0207s for 16384 events => throughput is 7.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0310s for 155440 events => throughput is 5.01E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1929s for 155440 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0700s for 16384 events => throughput is 2.34E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0206s for 16384 events => throughput is 7.97E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0309s for 155440 events => throughput is 5.02E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1538s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5867s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1538s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1541s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4960s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1541s for 16384 events => throughput is 1.06E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 5.7402 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 5.1794 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3686s + [COUNTERS] PROGRAM TOTAL : 1.2224s [COUNTERS] Fortran Other ( 0 ) : 0.0368s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3600s for 193303 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0802s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0046s for 16384 events => throughput is 3.58E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0128s for 193303 events => throughput is 1.51E+07 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2479s for 193303 events => throughput is 7.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0801s for 49152 events => throughput is 6.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0047s for 16384 events => throughput is 3.50E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0127s for 193303 events => throughput is 1.52E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7417s for 16384 events => throughput is 2.21E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6269s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7417s for 16384 events => throughput is 2.21E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7059s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5166s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7059s for 16384 events => throughput is 2.32E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G21/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7552s - [COUNTERS] Fortran Other ( 0 ) : 0.0538s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6833s for 430212 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0798s for 49152 events => throughput is 6.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1014s for 16384 events => throughput is 1.62E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5238s + [COUNTERS] Fortran Other ( 0 ) : 0.0528s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4526s for 430212 events => throughput is 9.51E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1028s for 16384 events => throughput is 1.59E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0175s for 16384 events => throughput is 9.39E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0335s for 430212 events => throughput is 1.28E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.47E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0331s for 430212 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7062s for 16384 events => throughput is 2.32E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0490s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7062s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7057s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8182s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7057s for 16384 events => throughput is 2.32E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2929s - [COUNTERS] Fortran Other ( 0 ) : 0.0317s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0407s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2893s for 154293 events => throughput is 5.33E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0807s for 49152 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0100s for 16384 events => throughput is 1.65E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0183s for 154293 events => throughput is 8.45E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] PROGRAM TOTAL : 1.2026s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1988s for 154293 events => throughput is 7.76E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0805s for 49152 events => throughput is 6.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0099s for 16384 events => throughput is 1.65E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.57E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7056s for 16384 events => throughput is 2.32E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5873s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7056s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7054s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4971s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7054s for 16384 events => throughput is 2.32E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2851s - [COUNTERS] Fortran Other ( 0 ) : 0.0316s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3184s for 159370 events => throughput is 5.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0798s for 49152 events => throughput is 6.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.05E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0131s for 159370 events => throughput is 1.22E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s + [COUNTERS] PROGRAM TOTAL : 1.1952s + [COUNTERS] Fortran Other ( 0 ) : 0.0317s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2281s for 159370 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0794s for 49152 events => throughput is 6.19E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.98E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.23E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0039s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7054s for 16384 events => throughput is 2.32E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5797s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7054s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7059s for 16384 events => throughput is 2.32E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4893s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7059s for 16384 events => throughput is 2.32E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.5946 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.1888 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8455s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3837s for 212440 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0714s for 49152 events => throughput is 6.88E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0681s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.73E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0203s for 16384 events => throughput is 8.08E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7228s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2621s for 212440 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0706s for 49152 events => throughput is 6.96E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0684s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0203s for 16384 events => throughput is 8.07E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.57E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6911s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1543s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1539s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5689s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1539s for 16384 events => throughput is 1.06E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8799s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4536s for 250568 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0709s for 49152 events => throughput is 6.93E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.77E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0127s for 16384 events => throughput is 1.29E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0242s for 250568 events => throughput is 1.04E+07 events/s + [COUNTERS] PROGRAM TOTAL : 0.7296s + [COUNTERS] Fortran Other ( 0 ) : 0.0409s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3046s for 250568 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0126s for 16384 events => throughput is 1.30E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0241s for 250568 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1546s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7253s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5749s [COUNTERS] OVERALL MEs ( 32 ) : 0.1546s for 16384 events => throughput is 1.06E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8422s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4117s for 227751 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0713s for 49152 events => throughput is 6.89E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0681s for 16384 events => throughput is 2.41E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0060s for 16384 events => throughput is 2.72E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.46E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] PROGRAM TOTAL : 0.7093s + [COUNTERS] Fortran Other ( 0 ) : 0.0367s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2783s for 227751 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0061s for 16384 events => throughput is 2.69E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.47E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1539s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6884s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1539s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1544s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5549s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1544s for 16384 events => throughput is 1.06E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.8072 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.7013 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7968s + [COUNTERS] PROGRAM TOTAL : 0.6909s [COUNTERS] Fortran Other ( 0 ) : 0.0332s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3561s for 184243 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0441s for 16384 events => throughput is 3.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.59E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 184243 events => throughput is 4.87E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2490s for 184243 events => throughput is 7.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0693s for 49152 events => throughput is 7.09E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.72E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0380s for 184243 events => throughput is 4.85E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6437s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5378s [COUNTERS] OVERALL MEs ( 32 ) : 0.1531s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 2.5523 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 1.9428 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/G14/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5413s - [COUNTERS] Fortran Other ( 0 ) : 0.0977s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8678s for 1143085 events => throughput is 6.12E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0710s for 49152 events => throughput is 6.92E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9323s + [COUNTERS] Fortran Other ( 0 ) : 0.0966s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2625s for 1143085 events => throughput is 9.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0685s for 49152 events => throughput is 7.17E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0565s for 16384 events => throughput is 2.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0109s for 16384 events => throughput is 1.50E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0433s for 1143085 events => throughput is 2.64E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0428s for 1143085 events => throughput is 2.67E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.3148s for 16384 events => throughput is 5.20E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2265s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6175s [COUNTERS] OVERALL MEs ( 32 ) : 0.3148s for 16384 events => throughput is 5.20E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 5.5152 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 5.2043 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0066s - [COUNTERS] Fortran Other ( 0 ) : 0.0468s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6175s for 332018 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8997s + [COUNTERS] Fortran Other ( 0 ) : 0.0456s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4232s for 332018 events => throughput is 7.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0790s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0786s for 332018 events => throughput is 4.22E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0002s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0063s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0002s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0532s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0786s for 332018 events => throughput is 4.23E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0882s for 16384 events => throughput is 1.51E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8116s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0882s for 16384 events => throughput is 1.51E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7731s - [COUNTERS] Fortran Other ( 0 ) : 0.0348s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3393s for 183011 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.04E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0629s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0991s for 183011 events => throughput is 1.85E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.6657s + [COUNTERS] Fortran Other ( 0 ) : 0.0345s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2345s for 183011 events => throughput is 7.81E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0629s for 16384 events => throughput is 2.61E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0990s for 183011 events => throughput is 1.85E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0004s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7727s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0004s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9999s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6658s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9999s for 16384 events => throughput is 1.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7087s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3477s for 193329 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0693s for 49152 events => throughput is 7.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0355s for 16384 events => throughput is 4.61E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0608s for 193329 events => throughput is 3.18E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.6121s + [COUNTERS] Fortran Other ( 0 ) : 0.0365s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2496s for 193329 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0355s for 16384 events => throughput is 4.62E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0609s for 193329 events => throughput is 3.18E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9998s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7090s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9998s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0005s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6116s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0005s for 16384 events => throughput is 1.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.8959 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.7547 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8858s - [COUNTERS] Fortran Other ( 0 ) : 0.0396s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4366s for 243014 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0667s for 49152 events => throughput is 7.37E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.76E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7440s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2941s for 243014 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0666s for 49152 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.77E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0259s for 16384 events => throughput is 6.33E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 243014 events => throughput is 5.90E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0413s for 243014 events => throughput is 5.88E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1541s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7317s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5899s [COUNTERS] OVERALL MEs ( 32 ) : 0.1541s for 16384 events => throughput is 1.06E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.8275 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.6681 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9141s - [COUNTERS] Fortran Other ( 0 ) : 0.0316s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0409s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2775s for 152585 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0801s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0049s for 16384 events => throughput is 3.32E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.8251s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1860s for 152585 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0800s for 49152 events => throughput is 6.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0816s for 16384 events => throughput is 2.01E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0048s for 16384 events => throughput is 3.39E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0122s for 152585 events => throughput is 1.25E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3472s for 16384 events => throughput is 4.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5669s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3472s for 16384 events => throughput is 4.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3489s for 16384 events => throughput is 4.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4762s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3489s for 16384 events => throughput is 4.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G62/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8947s + [COUNTERS] PROGRAM TOTAL : 0.8240s [COUNTERS] Fortran Other ( 0 ) : 0.0294s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2222s for 121146 events => throughput is 5.45E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1508s for 121146 events => throughput is 8.04E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0799s for 49152 events => throughput is 6.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0833s for 16384 events => throughput is 1.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0207s for 16384 events => throughput is 7.93E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0842s for 16384 events => throughput is 1.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0206s for 16384 events => throughput is 7.94E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0321s for 121146 events => throughput is 3.77E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0040s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3477s for 16384 events => throughput is 4.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5470s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3477s for 16384 events => throughput is 4.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3473s for 16384 events => throughput is 4.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4766s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3473s for 16384 events => throughput is 4.72E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 2.0538 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 1.8599 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0432s - [COUNTERS] Fortran Other ( 0 ) : 0.0421s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6548s for 329671 events => throughput is 5.03E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0509s for 16384 events => throughput is 3.22E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8493s + [COUNTERS] Fortran Other ( 0 ) : 0.0418s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4629s for 329671 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0508s for 16384 events => throughput is 3.23E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0816s for 329671 events => throughput is 4.04E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0810s for 329671 events => throughput is 4.07E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0429s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0003s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9999s for 16384 events => throughput is 1.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8494s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9999s for 16384 events => throughput is 1.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.9854 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.8345 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/G7/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9750s - [COUNTERS] Fortran Other ( 0 ) : 0.0400s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4915s for 255151 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0831s for 81920 events => throughput is 9.85E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0416s for 16384 events => throughput is 3.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0510s for 255151 events => throughput is 5.01E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.8241s + [COUNTERS] Fortran Other ( 0 ) : 0.0396s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3425s for 255151 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.90E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0415s for 16384 events => throughput is 3.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0506s for 255151 events => throughput is 5.04E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1545s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8205s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1545s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1546s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6695s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1546s for 16384 events => throughput is 1.06E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.5265 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.3125 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.6928s - [COUNTERS] Fortran Other ( 0 ) : 0.0334s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2929s for 159224 events => throughput is 5.44E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.5962s + [COUNTERS] Fortran Other ( 0 ) : 0.0337s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1966s for 159224 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0441s for 16384 events => throughput is 3.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.98E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0133s for 159224 events => throughput is 1.20E+07 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.97E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0132s for 159224 events => throughput is 1.21E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1542s for 16384 events => throughput is 1.06E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5386s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1542s for 16384 events => throughput is 1.06E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1538s for 16384 events => throughput is 1.07E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4423s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1538s for 16384 events => throughput is 1.07E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8154s - [COUNTERS] Fortran Other ( 0 ) : 0.0345s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3907s for 201854 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0165s for 16384 events => throughput is 9.90E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0277s for 201854 events => throughput is 7.30E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.6978s + [COUNTERS] Fortran Other ( 0 ) : 0.0346s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2740s for 201854 events => throughput is 7.37E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0165s for 16384 events => throughput is 9.95E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.32E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1535s for 16384 events => throughput is 1.07E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6619s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5443s [COUNTERS] OVERALL MEs ( 32 ) : 0.1535s for 16384 events => throughput is 1.07E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 1.0890 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 0.9307 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0773s - [COUNTERS] Fortran Other ( 0 ) : 0.0427s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4984s for 268443 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.80E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0094s for 16384 events => throughput is 1.75E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0205s for 268443 events => throughput is 1.31E+07 events/s + [COUNTERS] PROGRAM TOTAL : 0.9195s + [COUNTERS] Fortran Other ( 0 ) : 0.0424s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3401s for 268443 events => throughput is 7.89E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0697s for 49152 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0096s for 16384 events => throughput is 1.71E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0206s for 268443 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3146s for 16384 events => throughput is 5.21E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7628s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3146s for 16384 events => throughput is 5.21E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3144s for 16384 events => throughput is 5.21E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6051s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3144s for 16384 events => throughput is 5.21E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.9041 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.8031 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8936s - [COUNTERS] Fortran Other ( 0 ) : 0.0326s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3162s for 168484 events => throughput is 5.33E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0666s for 16384 events => throughput is 2.46E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7927s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2166s for 168484 events => throughput is 7.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0660s for 16384 events => throughput is 2.48E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 4.97E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.58E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 5.01E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.57E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3140s for 16384 events => throughput is 5.22E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5796s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3140s for 16384 events => throughput is 5.22E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3137s for 16384 events => throughput is 5.22E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4790s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3137s for 16384 events => throughput is 5.22E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 180.7996 seconds -__CUDACPP_DEBUG: gen_ximprove.launch finished in 181.3542 seconds -__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 181.3548 seconds +__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 155.8258 seconds +__CUDACPP_DEBUG: gen_ximprove.launch finished in 156.3802 seconds +__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 156.3810 seconds __CUDACPP_DEBUG: GridPackCmd.launch (3a) combine_events combine_events __CUDACPP_DEBUG: GridPackCmd.launch (3b) store_events @@ -2116,9 +2116,9 @@ store_events INFO: No version of lhapdf. Can not run systematics computation decay_events -from_cards -__CUDACPP_DEBUG: GridPackCmd.launch finished in 184.0201 seconds +__CUDACPP_DEBUG: GridPackCmd.launch finished in 159.0310 seconds __CUDACPP_DEBUG: GridPackCmd.__init__ back from self.launch DONE write ./events.lhe.gz -END: Thu Aug 22 03:58:22 PM CEST 2024 -ELAPSED: 184 seconds +END: Thu Aug 22 05:11:21 PM CEST 2024 +ELAPSED: 159 seconds diff --git a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512z/output.txt b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512z/output.txt index 2a794462b2..6a2f60079a 100644 --- a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512z/output.txt +++ b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cpp512z/output.txt @@ -1,91 +1,91 @@ -START: Thu Aug 22 03:58:39 PM CEST 2024 +START: Thu Aug 22 05:11:38 PM CEST 2024 On itgold91.cern.ch [CPU: Intel(R) Xeon(R) Gold 6326 CPU (nproc=32)] [GPU: none]: CUDACPP_RUNTIME_DISABLEFPE is set -CUDACPP_RUNTIME_SKIPXBINCHECKS is not set -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:58 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +CUDACPP_RUNTIME_SKIPXBINCHECKS is set +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:11 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.512z_m_inl0_hrd0/madevent_cpp Now generating 100 events with random seed 21 and granularity 1 ************************************************************ * * @@ -211,1900 +211,1900 @@ __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event starting INFO: need to improve 108 channels __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 16.1815 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 13.9950 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9901s - [COUNTERS] Fortran Other ( 0 ) : 0.0339s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3225s for 176708 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0769s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0464s for 16384 events => throughput is 3.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0684s for 176708 events => throughput is 2.58E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9033s + [COUNTERS] Fortran Other ( 0 ) : 0.0347s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2242s for 176708 events => throughput is 7.88E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0887s for 81920 events => throughput is 9.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0465s for 16384 events => throughput is 3.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0688s for 176708 events => throughput is 2.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7051s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6183s [COUNTERS] OVERALL MEs ( 32 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2107s - [COUNTERS] Fortran Other ( 0 ) : 0.0473s + [COUNTERS] PROGRAM TOTAL : 1.0093s + [COUNTERS] Fortran Other ( 0 ) : 0.0462s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6074s for 337001 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4066s for 337001 events => throughput is 8.29E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0536s for 16384 events => throughput is 3.05E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0216s for 16384 events => throughput is 7.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0377s for 337001 events => throughput is 8.94E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 337001 events => throughput is 8.89E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9242s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7227s [COUNTERS] OVERALL MEs ( 32 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1049s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3790s for 196960 events => throughput is 5.20E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9673s + [COUNTERS] Fortran Other ( 0 ) : 0.0357s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2413s for 196960 events => throughput is 8.16E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0671s for 16384 events => throughput is 2.44E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0670s for 16384 events => throughput is 2.44E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1029s for 196960 events => throughput is 1.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2848s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8201s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2848s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6823s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2593s - [COUNTERS] Fortran Other ( 0 ) : 0.0427s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6266s for 324156 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0528s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0744s + [COUNTERS] Fortran Other ( 0 ) : 0.0424s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4366s for 324156 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0381s for 16384 events => throughput is 4.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 324156 events => throughput is 5.82E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0567s for 324156 events => throughput is 5.72E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9728s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2914s for 16384 events => throughput is 5.62E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7830s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2914s for 16384 events => throughput is 5.62E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9417s - [COUNTERS] Fortran Other ( 0 ) : 0.0357s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3046s for 176248 events => throughput is 5.79E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0804s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8385s + [COUNTERS] Fortran Other ( 0 ) : 0.0354s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1992s for 176248 events => throughput is 8.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0806s for 16384 events => throughput is 2.03E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0574s for 176248 events => throughput is 3.07E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0304s for 16384 events => throughput is 5.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0578s for 176248 events => throughput is 3.05E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2855s for 16384 events => throughput is 5.74E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6562s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2855s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5516s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8635s - [COUNTERS] Fortran Other ( 0 ) : 0.0308s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2499s for 128162 events => throughput is 5.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7869s + [COUNTERS] Fortran Other ( 0 ) : 0.0312s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1739s for 128162 events => throughput is 7.37E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0772s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0361s for 16384 events => throughput is 4.54E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0362s for 16384 events => throughput is 4.53E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0500s for 128162 events => throughput is 2.56E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2852s for 16384 events => throughput is 5.74E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5783s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2852s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5021s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G2/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8815s - [COUNTERS] Fortran Other ( 0 ) : 0.0673s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2153s for 680231 events => throughput is 5.60E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5133s + [COUNTERS] Fortran Other ( 0 ) : 0.0670s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8473s for 680231 events => throughput is 8.03E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0847s for 16384 events => throughput is 1.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.76E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0482s for 680231 events => throughput is 1.41E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0846s for 16384 events => throughput is 1.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.79E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0483s for 680231 events => throughput is 1.41E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5965s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2284s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0585s - [COUNTERS] Fortran Other ( 0 ) : 0.0404s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3924s for 227876 events => throughput is 5.81E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0768s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9193s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2539s for 227876 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0761s for 16384 events => throughput is 2.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0334s for 16384 events => throughput is 4.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 227876 events => throughput is 3.13E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0729s for 227876 events => throughput is 3.13E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7736s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2855s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6338s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2855s for 16384 events => throughput is 5.74E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1012s - [COUNTERS] Fortran Other ( 0 ) : 0.0397s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5024s for 258529 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0383s for 258529 events => throughput is 6.76E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9482s + [COUNTERS] Fortran Other ( 0 ) : 0.0398s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3505s for 258529 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.79E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0384s for 258529 events => throughput is 6.74E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8143s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6613s [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G75/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2162s - [COUNTERS] Fortran Other ( 0 ) : 0.0441s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0430s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5322s for 288195 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0394s + [COUNTERS] Fortran Other ( 0 ) : 0.0437s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3555s for 288195 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0583s for 16384 events => throughput is 2.81E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0817s for 288195 events => throughput is 3.53E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9292s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2871s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7523s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2871s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4927s - [COUNTERS] Fortran Other ( 0 ) : 0.0488s + [COUNTERS] PROGRAM TOTAL : 1.2779s + [COUNTERS] Fortran Other ( 0 ) : 0.0496s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6509s for 362045 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0640s for 16384 events => throughput is 2.56E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1121s for 16384 events => throughput is 1.46E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1752s for 362045 events => throughput is 2.07E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4422s for 362045 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0639s for 16384 events => throughput is 2.56E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1098s for 16384 events => throughput is 1.49E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1708s for 362045 events => throughput is 2.12E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2077s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9928s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9962s - [COUNTERS] Fortran Other ( 0 ) : 0.0402s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3284s for 203191 events => throughput is 6.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.8742s + [COUNTERS] Fortran Other ( 0 ) : 0.0401s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2073s for 203191 events => throughput is 9.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0368s for 16384 events => throughput is 4.46E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0673s for 203191 events => throughput is 3.02E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0369s for 16384 events => throughput is 4.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0671s for 203191 events => throughput is 3.03E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7094s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5873s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9233s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3789s for 205739 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0693s for 49152 events => throughput is 7.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0058s for 16384 events => throughput is 2.82E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7990s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2544s for 205739 events => throughput is 8.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0058s for 16384 events => throughput is 2.85E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.42E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2853s for 16384 events => throughput is 5.74E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6380s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2853s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5140s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2850s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0210s + [COUNTERS] PROGRAM TOTAL : 0.8951s [COUNTERS] Fortran Other ( 0 ) : 0.0392s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3670s for 214038 events => throughput is 5.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2406s for 214038 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0805s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0671s for 214038 events => throughput is 3.19E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0669s for 214038 events => throughput is 3.20E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7361s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6102s [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 3.9061 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 3.4163 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4231s - [COUNTERS] Fortran Other ( 0 ) : 0.0492s + [COUNTERS] PROGRAM TOTAL : 1.2230s + [COUNTERS] Fortran Other ( 0 ) : 0.0498s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6178s for 344023 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0834s for 81920 events => throughput is 9.82E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0571s for 16384 events => throughput is 2.87E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1009s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1454s for 344023 events => throughput is 2.37E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4176s for 344023 events => throughput is 8.24E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0831s for 81920 events => throughput is 9.86E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0565s for 16384 events => throughput is 2.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1011s for 16384 events => throughput is 1.62E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1457s for 344023 events => throughput is 2.36E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2905s for 16384 events => throughput is 5.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1326s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2905s for 16384 events => throughput is 5.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2907s for 16384 events => throughput is 5.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9323s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2907s for 16384 events => throughput is 5.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G43/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1826s - [COUNTERS] Fortran Other ( 0 ) : 0.0389s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4096s for 214181 events => throughput is 5.23E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1355s for 212992 events => throughput is 1.57E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0611s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0440s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2859s for 214181 events => throughput is 7.49E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1354s for 212992 events => throughput is 1.57E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0708s for 16384 events => throughput is 2.31E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0996s for 214181 events => throughput is 2.15E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0710s for 16384 events => throughput is 2.31E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 214181 events => throughput is 2.16E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2906s for 16384 events => throughput is 5.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8920s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2906s for 16384 events => throughput is 5.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2908s for 16384 events => throughput is 5.63E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7703s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2908s for 16384 events => throughput is 5.63E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2719s - [COUNTERS] Fortran Other ( 0 ) : 0.0422s + [COUNTERS] PROGRAM TOTAL : 1.1045s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5417s for 279555 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1135s for 147456 events => throughput is 1.30E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3752s for 279555 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1132s for 147456 events => throughput is 1.30E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0619s for 16384 events => throughput is 2.65E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0618s for 16384 events => throughput is 2.65E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0861s for 279555 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2909s for 16384 events => throughput is 5.63E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9810s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2909s for 16384 events => throughput is 5.63E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2907s for 16384 events => throughput is 5.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8138s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2907s for 16384 events => throughput is 5.64E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 1.9364 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 1.5946 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/G67/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9236s - [COUNTERS] Fortran Other ( 0 ) : 0.0788s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2741s for 814370 events => throughput is 6.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1110s for 16384 events => throughput is 1.48E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0305s for 16384 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0595s for 814370 events => throughput is 1.37E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.5830s + [COUNTERS] Fortran Other ( 0 ) : 0.1733s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8411s for 814370 events => throughput is 9.68E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0794s for 49152 events => throughput is 6.19E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1106s for 16384 events => throughput is 1.48E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0306s for 16384 events => throughput is 5.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0592s for 814370 events => throughput is 1.37E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0004s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2098s for 16384 events => throughput is 7.81E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7138s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2098s for 16384 events => throughput is 7.81E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2095s for 16384 events => throughput is 7.82E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3735s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2095s for 16384 events => throughput is 7.82E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 9.2142 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 7.9707 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7600s - [COUNTERS] Fortran Other ( 0 ) : 0.0835s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5492s for 933480 events => throughput is 6.03E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0773s for 49152 events => throughput is 6.36E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1014s for 16384 events => throughput is 1.61E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1004s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1611s for 933480 events => throughput is 5.80E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.2562s + [COUNTERS] Fortran Other ( 0 ) : 0.0820s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0473s for 933480 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1014s for 16384 events => throughput is 1.62E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1005s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1600s for 933480 events => throughput is 5.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6077s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1523s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6077s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6076s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6487s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6076s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5031s - [COUNTERS] Fortran Other ( 0 ) : 0.0356s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4254s for 226350 events => throughput is 5.32E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3688s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2904s for 226350 events => throughput is 7.79E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0766s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0797s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0799s for 16384 events => throughput is 2.05E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1220s for 226350 events => throughput is 1.86E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6071s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8960s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6071s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6073s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7615s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6073s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6736s - [COUNTERS] Fortran Other ( 0 ) : 0.0532s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6483s for 323984 events => throughput is 5.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0503s for 16384 events => throughput is 3.26E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4711s + [COUNTERS] Fortran Other ( 0 ) : 0.0415s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4596s for 323984 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0500s for 16384 events => throughput is 3.28E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0634s for 16384 events => throughput is 2.59E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0933s for 323984 events => throughput is 3.47E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0634s for 16384 events => throughput is 2.58E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0930s for 323984 events => throughput is 3.48E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0655s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6070s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8640s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6070s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7241s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s + [COUNTERS] PROGRAM TOTAL : 1.5180s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7119s for 355559 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0501s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0623s for 16384 events => throughput is 2.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0930s for 355559 events => throughput is 3.82E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5044s for 355559 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0505s for 16384 events => throughput is 3.24E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0624s for 16384 events => throughput is 2.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0928s for 355559 events => throughput is 3.83E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1160s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6083s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9097s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6083s for 16384 events => throughput is 2.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G92/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4890s - [COUNTERS] Fortran Other ( 0 ) : 0.0662s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4554s for 255849 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3117s + [COUNTERS] Fortran Other ( 0 ) : 0.0412s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3040s for 255849 events => throughput is 8.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0389s for 16384 events => throughput is 4.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0848s for 255849 events => throughput is 3.02E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0388s for 16384 events => throughput is 4.22E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0839s for 255849 events => throughput is 3.05E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6090s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8800s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6090s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6092s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7025s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6092s for 16384 events => throughput is 2.69E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 9.3936 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 7.7363 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5089s - [COUNTERS] Fortran Other ( 0 ) : 0.0780s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4089s for 859290 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1061s for 16384 events => throughput is 1.54E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0588s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0989s for 859290 events => throughput is 8.69E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.0785s + [COUNTERS] Fortran Other ( 0 ) : 0.0774s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9581s for 859290 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0754s for 81920 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1063s for 16384 events => throughput is 1.54E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0576s for 16384 events => throughput is 2.84E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0980s for 859290 events => throughput is 8.76E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6022s for 16384 events => throughput is 2.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9067s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6022s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6263s for 16384 events => throughput is 2.62E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4521s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6263s for 16384 events => throughput is 2.62E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7757s - [COUNTERS] Fortran Other ( 0 ) : 0.0927s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.7913s for 1098402 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0124s for 16384 events => throughput is 1.32E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.56E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.2116s + [COUNTERS] Fortran Other ( 0 ) : 0.0918s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2125s for 1098402 events => throughput is 9.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0125s for 16384 events => throughput is 1.32E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0429s for 1098402 events => throughput is 2.56E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6017s for 16384 events => throughput is 2.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1740s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6017s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6177s for 16384 events => throughput is 2.65E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5939s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6177s for 16384 events => throughput is 2.65E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7549s - [COUNTERS] Fortran Other ( 0 ) : 0.0541s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7476s for 378380 events => throughput is 5.06E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0848s for 378380 events => throughput is 4.46E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.5278s + [COUNTERS] Fortran Other ( 0 ) : 0.0445s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5303s for 378380 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0568s for 16384 events => throughput is 2.88E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0847s for 378380 events => throughput is 4.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6024s for 16384 events => throughput is 2.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1524s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6024s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6019s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9258s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6019s for 16384 events => throughput is 2.72E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G65/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3169s - [COUNTERS] Fortran Other ( 0 ) : 0.0733s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3548s for 819579 events => throughput is 6.05E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0812s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8827s + [COUNTERS] Fortran Other ( 0 ) : 0.0726s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9215s for 819579 events => throughput is 8.89E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0810s for 16384 events => throughput is 2.02E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0146s for 16384 events => throughput is 1.13E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0392s for 819579 events => throughput is 2.09E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0146s for 16384 events => throughput is 1.12E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0391s for 819579 events => throughput is 2.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6059s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7110s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6059s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6068s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2759s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6068s for 16384 events => throughput is 2.70E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.2396 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.0406 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2277s - [COUNTERS] Fortran Other ( 0 ) : 0.0446s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6365s for 330261 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0870s for 81920 events => throughput is 9.41E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0298s + [COUNTERS] Fortran Other ( 0 ) : 0.0434s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4449s for 330261 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0866s for 81920 events => throughput is 9.46E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.89E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0074s for 16384 events => throughput is 2.21E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0198s for 330261 events => throughput is 1.67E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0074s for 16384 events => throughput is 2.22E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0196s for 330261 events => throughput is 1.68E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2966s for 16384 events => throughput is 5.52E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9311s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2966s for 16384 events => throughput is 5.52E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2926s for 16384 events => throughput is 5.60E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7372s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2926s for 16384 events => throughput is 5.60E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 2.1820 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 1.6762 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1710s - [COUNTERS] Fortran Other ( 0 ) : 0.0838s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4404s for 919173 events => throughput is 6.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.19E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0838s for 16384 events => throughput is 1.96E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1316s for 919173 events => throughput is 6.99E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.6656s + [COUNTERS] Fortran Other ( 0 ) : 0.0829s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9356s for 919173 events => throughput is 9.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0686s for 49152 events => throughput is 7.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0840s for 16384 events => throughput is 1.95E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1313s for 919173 events => throughput is 7.00E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2053s for 16384 events => throughput is 7.98E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9657s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2053s for 16384 events => throughput is 7.98E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2056s for 16384 events => throughput is 7.97E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4600s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2056s for 16384 events => throughput is 7.97E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 12.3336 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 9.9190 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9643s - [COUNTERS] Fortran Other ( 0 ) : 0.0320s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2785s for 142763 events => throughput is 5.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0649s for 16384 events => throughput is 2.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0903s for 142763 events => throughput is 1.58E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 0.8803s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1940s for 142763 events => throughput is 7.36E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0767s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0650s for 16384 events => throughput is 2.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0900s for 142763 events => throughput is 1.59E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6762s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2877s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5926s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2877s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7709s - [COUNTERS] Fortran Other ( 0 ) : 0.0977s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8395s for 1119813 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1106s for 16384 events => throughput is 1.48E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1084s for 16384 events => throughput is 1.51E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1716s for 1119813 events => throughput is 6.52E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.1733s + [COUNTERS] Fortran Other ( 0 ) : 0.0970s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2444s for 1119813 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1098s for 16384 events => throughput is 1.49E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1080s for 16384 events => throughput is 1.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1710s for 1119813 events => throughput is 6.55E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2876s for 16384 events => throughput is 5.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4833s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2876s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8858s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9375s - [COUNTERS] Fortran Other ( 0 ) : 0.1097s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2242s for 1357398 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0869s for 16384 events => throughput is 1.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 1357398 events => throughput is 2.44E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 2.2132s + [COUNTERS] Fortran Other ( 0 ) : 0.1089s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5021s for 1357398 events => throughput is 9.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0868s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0175s for 16384 events => throughput is 9.38E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0554s for 1357398 events => throughput is 2.45E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6498s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9258s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5362s - [COUNTERS] Fortran Other ( 0 ) : 0.0521s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7157s for 398526 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3019s + [COUNTERS] Fortran Other ( 0 ) : 0.0513s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4789s for 398526 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1144s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1649s for 398526 events => throughput is 2.42E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1143s for 16384 events => throughput is 1.43E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1682s for 398526 events => throughput is 2.37E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2485s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2874s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0145s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2874s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G53/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9017s - [COUNTERS] Fortran Other ( 0 ) : 0.0908s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9726s for 1103762 events => throughput is 5.60E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0767s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0872s for 16384 events => throughput is 1.88E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.2954s + [COUNTERS] Fortran Other ( 0 ) : 0.0898s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3682s for 1103762 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0858s for 16384 events => throughput is 1.91E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1237s for 16384 events => throughput is 1.32E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1837s for 1103762 events => throughput is 6.01E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1206s for 16384 events => throughput is 1.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1873s for 1103762 events => throughput is 5.89E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6142s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0072s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1701s - [COUNTERS] Fortran Other ( 0 ) : 0.0446s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4680s for 272273 events => throughput is 5.82E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0605s for 16384 events => throughput is 2.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1097s for 272273 events => throughput is 2.48E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 1.0033s + [COUNTERS] Fortran Other ( 0 ) : 0.0440s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3055s for 272273 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0583s for 16384 events => throughput is 2.81E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1094s for 272273 events => throughput is 2.49E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8835s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2866s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2859s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7173s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2859s for 16384 events => throughput is 5.73E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 0.9534 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 0.8896 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/G71/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9426s - [COUNTERS] Fortran Other ( 0 ) : 0.0289s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2207s for 109714 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0819s for 49152 events => throughput is 6.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0167s for 16384 events => throughput is 9.81E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.38E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 0.8784s + [COUNTERS] Fortran Other ( 0 ) : 0.0284s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1574s for 109714 events => throughput is 6.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0820s for 49152 events => throughput is 6.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0167s for 16384 events => throughput is 9.79E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.39E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4357s for 16384 events => throughput is 3.76E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5070s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4357s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4351s for 16384 events => throughput is 3.77E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4433s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4351s for 16384 events => throughput is 3.77E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.0932 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 1.5822 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0821s - [COUNTERS] Fortran Other ( 0 ) : 0.0875s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4845s for 949349 events => throughput is 6.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0790s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0648s for 16384 events => throughput is 2.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 949349 events => throughput is 8.73E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.5714s + [COUNTERS] Fortran Other ( 0 ) : 0.0860s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9768s for 949349 events => throughput is 9.72E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1084s for 949349 events => throughput is 8.76E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1004s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9817s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1004s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1000s for 16384 events => throughput is 1.64E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4715s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1000s for 16384 events => throughput is 1.64E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 4.7990 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 4.2676 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3779s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3403s for 181152 events => throughput is 5.32E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0773s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0591s for 16384 events => throughput is 2.77E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2613s + [COUNTERS] Fortran Other ( 0 ) : 0.0366s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2322s for 181152 events => throughput is 7.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0590s for 16384 events => throughput is 2.78E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0903s for 181152 events => throughput is 2.01E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6172s for 16384 events => throughput is 2.65E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7607s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6172s for 16384 events => throughput is 2.65E+04 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6067s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6546s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6067s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6004s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5882s for 293756 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4253s + [COUNTERS] Fortran Other ( 0 ) : 0.0416s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4153s for 293756 events => throughput is 7.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0658s for 16384 events => throughput is 2.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0922s for 293756 events => throughput is 3.19E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0921s for 293756 events => throughput is 3.19E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6016s for 16384 events => throughput is 2.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9988s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6016s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6018s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8235s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6018s for 16384 events => throughput is 2.72E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7931s - [COUNTERS] Fortran Other ( 0 ) : 0.0523s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7545s for 405834 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0742s for 16384 events => throughput is 2.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1087s for 405834 events => throughput is 3.73E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.5539s + [COUNTERS] Fortran Other ( 0 ) : 0.0520s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5152s for 405834 events => throughput is 7.88E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0745s for 16384 events => throughput is 2.20E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1086s for 405834 events => throughput is 3.74E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6024s for 16384 events => throughput is 2.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1908s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6024s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6026s for 16384 events => throughput is 2.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9513s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6026s for 16384 events => throughput is 2.72E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 15.1006 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 12.9343 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5817s - [COUNTERS] Fortran Other ( 0 ) : 0.0778s + [COUNTERS] PROGRAM TOTAL : 2.1111s + [COUNTERS] Fortran Other ( 0 ) : 0.0775s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4293s for 847188 events => throughput is 5.93E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1029s for 16384 events => throughput is 1.59E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9636s for 847188 events => throughput is 8.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1030s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1226s for 847188 events => throughput is 6.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6152s for 16384 events => throughput is 2.66E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9665s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6152s for 16384 events => throughput is 2.66E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6101s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5010s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6101s for 16384 events => throughput is 2.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3036s - [COUNTERS] Fortran Other ( 0 ) : 0.0333s + [COUNTERS] PROGRAM TOTAL : 1.2002s + [COUNTERS] Fortran Other ( 0 ) : 0.0332s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3146s for 167274 events => throughput is 5.32E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0831s for 16384 events => throughput is 1.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2184s for 167274 events => throughput is 7.66E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0448s for 16384 events => throughput is 3.66E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0635s for 167274 events => throughput is 2.63E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0634s for 167274 events => throughput is 2.64E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6085s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6951s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6085s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6062s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5940s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6062s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9133s - [COUNTERS] Fortran Other ( 0 ) : 0.0980s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8844s for 1150245 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0777s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0262s for 16384 events => throughput is 6.26E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0610s for 1150245 events => throughput is 1.89E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] PROGRAM TOTAL : 2.3037s + [COUNTERS] Fortran Other ( 0 ) : 0.0976s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2753s for 1150245 events => throughput is 9.02E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0257s for 16384 events => throughput is 6.38E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0597s for 1150245 events => throughput is 1.93E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6109s for 16384 events => throughput is 2.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3025s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6109s for 16384 events => throughput is 2.68E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6115s for 16384 events => throughput is 2.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6921s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6115s for 16384 events => throughput is 2.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6027s - [COUNTERS] Fortran Other ( 0 ) : 0.0478s + [COUNTERS] PROGRAM TOTAL : 1.3992s + [COUNTERS] Fortran Other ( 0 ) : 0.0476s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6593s for 355348 events => throughput is 5.39E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4536s for 355348 events => throughput is 7.83E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0296s for 16384 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 355348 events => throughput is 7.42E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0298s for 16384 events => throughput is 5.49E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 355348 events => throughput is 7.44E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6098s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9929s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6098s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6107s for 16384 events => throughput is 2.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7885s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6107s for 16384 events => throughput is 2.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5693s - [COUNTERS] Fortran Other ( 0 ) : 0.0788s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4159s for 864266 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1064s for 16384 events => throughput is 1.54E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1285s for 864266 events => throughput is 6.72E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 2.1309s + [COUNTERS] Fortran Other ( 0 ) : 0.0784s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9797s for 864266 events => throughput is 8.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0756s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1055s for 16384 events => throughput is 1.55E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1278s for 864266 events => throughput is 6.76E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6058s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9634s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6058s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6060s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5249s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6060s for 16384 events => throughput is 2.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5621s - [COUNTERS] Fortran Other ( 0 ) : 0.0405s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5661s for 285525 events => throughput is 5.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.4104s + [COUNTERS] Fortran Other ( 0 ) : 0.0397s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4010s for 285525 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0588s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0805s for 285525 events => throughput is 3.55E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0586s for 16384 events => throughput is 2.79E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0802s for 285525 events => throughput is 3.56E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6055s for 16384 events => throughput is 2.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9567s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6055s for 16384 events => throughput is 2.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6207s for 16384 events => throughput is 2.64E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7898s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6207s for 16384 events => throughput is 2.64E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3021s - [COUNTERS] Fortran Other ( 0 ) : 0.0371s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3413s for 189666 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.19E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1871s + [COUNTERS] Fortran Other ( 0 ) : 0.0369s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2276s for 189666 events => throughput is 8.33E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0808s for 16384 events => throughput is 2.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0300s for 16384 events => throughput is 5.46E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0532s for 189666 events => throughput is 3.56E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0299s for 16384 events => throughput is 5.48E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0549s for 189666 events => throughput is 3.46E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6113s for 16384 events => throughput is 2.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6908s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6113s for 16384 events => throughput is 2.68E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6103s for 16384 events => throughput is 2.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5768s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6103s for 16384 events => throughput is 2.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1962s - [COUNTERS] Fortran Other ( 0 ) : 0.0307s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2484s for 124553 events => throughput is 5.01E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1224s + [COUNTERS] Fortran Other ( 0 ) : 0.0305s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1758s for 124553 events => throughput is 7.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0756s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.01E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0425s for 16384 events => throughput is 3.86E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0589s for 124553 events => throughput is 2.11E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0588s for 124553 events => throughput is 2.12E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6065s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5897s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6065s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6060s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5164s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6060s for 16384 events => throughput is 2.70E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 2.7176 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 2.3116 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G48/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3432s - [COUNTERS] Fortran Other ( 0 ) : 0.0447s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5860s for 318589 events => throughput is 5.44E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1434s + [COUNTERS] Fortran Other ( 0 ) : 0.0439s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3861s for 318589 events => throughput is 8.25E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0536s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0876s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1297s for 318589 events => throughput is 2.46E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1298s for 318589 events => throughput is 2.45E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0582s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2851s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8584s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3536s - [COUNTERS] Fortran Other ( 0 ) : 0.0438s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6675s for 343552 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1488s + [COUNTERS] Fortran Other ( 0 ) : 0.0430s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4630s for 343552 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0518s for 16384 events => throughput is 3.16E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0605s for 16384 events => throughput is 2.71E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0879s for 343552 events => throughput is 3.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0686s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2849s for 16384 events => throughput is 5.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2852s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8635s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2852s for 16384 events => throughput is 5.74E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 9.5152 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 7.9400 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1382s - [COUNTERS] Fortran Other ( 0 ) : 0.0359s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3989s for 223142 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0685s for 16384 events => throughput is 2.39E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1098s for 223142 events => throughput is 2.03E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 1.0079s + [COUNTERS] Fortran Other ( 0 ) : 0.0360s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2722s for 223142 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0686s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1093s for 223142 events => throughput is 2.04E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2873s for 16384 events => throughput is 5.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8509s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2873s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7210s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3158s - [COUNTERS] Fortran Other ( 0 ) : 0.0424s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6281s for 323723 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1191s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4343s for 323723 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0522s for 16384 events => throughput is 3.14E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0601s for 16384 events => throughput is 2.72E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0869s for 323723 events => throughput is 3.73E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0599s for 16384 events => throughput is 2.74E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0863s for 323723 events => throughput is 3.75E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0288s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8323s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1851s - [COUNTERS] Fortran Other ( 0 ) : 0.0378s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4396s for 243889 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0789s for 49152 events => throughput is 6.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0740s for 16384 events => throughput is 2.21E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0487s + [COUNTERS] Fortran Other ( 0 ) : 0.0372s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2986s for 243889 events => throughput is 8.17E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0739s for 16384 events => throughput is 2.22E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 243889 events => throughput is 2.24E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2871s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8980s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2871s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2927s for 16384 events => throughput is 5.60E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7559s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2927s for 16384 events => throughput is 5.60E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2800s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6191s for 320856 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0497s for 16384 events => throughput is 3.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 320856 events => throughput is 4.41E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0919s + [COUNTERS] Fortran Other ( 0 ) : 0.0411s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4322s for 320856 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0492s for 16384 events => throughput is 3.33E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 320856 events => throughput is 4.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9931s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8051s [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G34/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0091s - [COUNTERS] Fortran Other ( 0 ) : 0.1001s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0428s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2260s for 1259120 events => throughput is 5.66E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0870s for 16384 events => throughput is 1.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.3275s + [COUNTERS] Fortran Other ( 0 ) : 0.0980s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5524s for 1259120 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.32E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0867s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0504s for 16384 events => throughput is 3.25E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0963s for 1259120 events => throughput is 1.31E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0960s for 1259120 events => throughput is 1.31E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0033s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2905s for 16384 events => throughput is 5.64E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.7186s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2905s for 16384 events => throughput is 5.64E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2867s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0408s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2867s for 16384 events => throughput is 5.71E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5331s - [COUNTERS] Fortran Other ( 0 ) : 0.0516s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7242s for 403861 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0531s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1074s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1519s for 403861 events => throughput is 2.66E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2927s + [COUNTERS] Fortran Other ( 0 ) : 0.0496s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4875s for 403861 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1075s for 16384 events => throughput is 1.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1511s for 403861 events => throughput is 2.67E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2463s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0059s [COUNTERS] OVERALL MEs ( 32 ) : 0.2868s for 16384 events => throughput is 5.71E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 1.8803 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 1.5557 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9629s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s + [COUNTERS] PROGRAM TOTAL : 0.7952s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5520s for 285337 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0833s for 81920 events => throughput is 9.83E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0414s for 16384 events => throughput is 3.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0263s for 16384 events => throughput is 6.23E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3852s for 285337 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0831s for 81920 events => throughput is 9.85E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0406s for 16384 events => throughput is 4.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0261s for 16384 events => throughput is 6.28E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 285337 events => throughput is 6.92E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8643s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0989s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6963s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0989s for 16384 events => throughput is 1.66E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G46/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8987s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4758s for 258650 events => throughput is 5.44E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0421s for 16384 events => throughput is 3.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0379s for 16384 events => throughput is 4.32E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0539s for 258650 events => throughput is 4.80E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7415s + [COUNTERS] Fortran Other ( 0 ) : 0.0411s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3188s for 258650 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0426s for 16384 events => throughput is 3.84E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0378s for 16384 events => throughput is 4.33E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 258650 events => throughput is 4.81E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0997s for 16384 events => throughput is 1.64E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7990s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0997s for 16384 events => throughput is 1.64E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0996s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6420s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0996s for 16384 events => throughput is 1.65E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 2.2860 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 1.7988 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G25/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5006s - [COUNTERS] Fortran Other ( 0 ) : 0.0688s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0962s for 669977 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0630s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0031s for 16384 events => throughput is 5.21E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0221s for 669977 events => throughput is 3.04E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.1394s + [COUNTERS] Fortran Other ( 0 ) : 0.0680s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7368s for 669977 events => throughput is 9.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0638s for 16384 events => throughput is 2.57E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0032s for 16384 events => throughput is 5.19E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0217s for 669977 events => throughput is 3.09E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0992s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4014s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0992s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0984s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0410s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0984s for 16384 events => throughput is 1.66E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7660s - [COUNTERS] Fortran Other ( 0 ) : 0.0351s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3703s for 205420 events => throughput is 5.55E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6400s + [COUNTERS] Fortran Other ( 0 ) : 0.0345s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2510s for 205420 events => throughput is 8.18E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0723s for 16384 events => throughput is 2.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0678s for 16384 events => throughput is 2.42E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0152s for 16384 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.95E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0032s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.97E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6669s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5414s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 7.7758 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 6.7960 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1383s + [COUNTERS] PROGRAM TOTAL : 1.0118s [COUNTERS] Fortran Other ( 0 ) : 0.0361s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3922s for 218285 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0772s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0722s for 16384 events => throughput is 2.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1168s for 218285 events => throughput is 1.87E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2642s for 218285 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0724s for 16384 events => throughput is 2.26E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1163s for 218285 events => throughput is 1.88E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2864s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8519s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2864s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2874s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7244s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2874s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2046s + [COUNTERS] PROGRAM TOTAL : 1.0126s [COUNTERS] Fortran Other ( 0 ) : 0.0444s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5749s for 318651 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3837s for 318651 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0363s for 16384 events => throughput is 4.51E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0536s for 318651 events => throughput is 5.94E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0033s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0536s for 318651 events => throughput is 5.95E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2862s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9184s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2862s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2863s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7263s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2863s for 16384 events => throughput is 5.72E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9809s + [COUNTERS] PROGRAM TOTAL : 0.8837s [COUNTERS] Fortran Other ( 0 ) : 0.0330s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2981s for 164085 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0774s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0516s for 16384 events => throughput is 3.18E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0732s for 164085 events => throughput is 2.24E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2032s for 164085 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0516s for 16384 events => throughput is 3.17E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 164085 events => throughput is 2.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2895s for 16384 events => throughput is 5.66E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6914s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2895s for 16384 events => throughput is 5.66E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2893s for 16384 events => throughput is 5.66E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5944s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2893s for 16384 events => throughput is 5.66E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9723s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3437s for 177884 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8724s + [COUNTERS] Fortran Other ( 0 ) : 0.0343s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2415s for 177884 events => throughput is 7.37E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 4.00E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0573s for 177884 events => throughput is 3.10E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0414s for 16384 events => throughput is 3.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0572s for 177884 events => throughput is 3.11E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6862s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5863s [COUNTERS] OVERALL MEs ( 32 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9356s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3813s for 206659 events => throughput is 5.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8072s + [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2540s for 206659 events => throughput is 8.14E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0095s for 16384 events => throughput is 1.72E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0195s for 206659 events => throughput is 1.06E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6486s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2870s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5196s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2875s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9796s - [COUNTERS] Fortran Other ( 0 ) : 0.0371s + [COUNTERS] PROGRAM TOTAL : 0.8647s + [COUNTERS] Fortran Other ( 0 ) : 0.0360s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3355s for 195643 events => throughput is 5.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2208s for 195643 events => throughput is 8.86E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0325s for 16384 events => throughput is 5.04E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0602s for 195643 events => throughput is 3.25E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6927s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2869s for 16384 events => throughput is 5.71E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2876s for 16384 events => throughput is 5.70E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5770s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2876s for 16384 events => throughput is 5.70E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5023s - [COUNTERS] Fortran Other ( 0 ) : 0.0486s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6638s for 370750 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1139s for 16384 events => throughput is 1.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1775s for 370750 events => throughput is 2.09E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 1.2833s + [COUNTERS] Fortran Other ( 0 ) : 0.0479s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4455s for 370750 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1141s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1770s for 370750 events => throughput is 2.09E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2882s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2141s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2882s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2885s for 16384 events => throughput is 5.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9948s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2885s for 16384 events => throughput is 5.68E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.1154 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 1.5624 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/G42/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1041s - [COUNTERS] Fortran Other ( 0 ) : 0.0894s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5383s for 974583 events => throughput is 6.34E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5506s + [COUNTERS] Fortran Other ( 0 ) : 0.0896s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9843s for 974583 events => throughput is 9.90E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0782s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0941s for 974583 events => throughput is 1.04E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0032s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0584s for 16384 events => throughput is 2.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0939s for 974583 events => throughput is 1.04E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0989s for 16384 events => throughput is 1.66E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0052s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0989s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0992s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4515s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0992s for 16384 events => throughput is 1.65E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 24.5221 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 19.8924 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1529s - [COUNTERS] Fortran Other ( 0 ) : 0.0778s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4165s for 850849 events => throughput is 6.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6990s + [COUNTERS] Fortran Other ( 0 ) : 0.0776s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9653s for 850849 events => throughput is 8.81E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1101s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0369s for 16384 events => throughput is 4.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0677s for 850849 events => throughput is 1.26E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1085s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0370s for 16384 events => throughput is 4.42E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 850849 events => throughput is 1.27E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8648s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2881s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4110s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0730s - [COUNTERS] Fortran Other ( 0 ) : 0.0728s + [COUNTERS] PROGRAM TOTAL : 1.6496s + [COUNTERS] Fortran Other ( 0 ) : 0.0718s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3856s for 778343 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.09E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0888s for 16384 events => throughput is 1.85E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9618s for 778343 events => throughput is 8.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0895s for 16384 events => throughput is 1.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0287s for 16384 events => throughput is 5.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0549s for 778343 events => throughput is 1.42E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0545s for 778343 events => throughput is 1.43E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2879s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7851s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2879s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2884s for 16384 events => throughput is 5.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3611s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2884s for 16384 events => throughput is 5.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.6425s - [COUNTERS] Fortran Other ( 0 ) : 0.1002s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9579s for 1190413 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9951s + [COUNTERS] Fortran Other ( 0 ) : 0.1001s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3095s for 1190413 events => throughput is 9.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0862s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0107s for 16384 events => throughput is 1.53E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0443s for 1190413 events => throughput is 2.68E+07 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0108s for 16384 events => throughput is 1.51E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0442s for 1190413 events => throughput is 2.70E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2884s for 16384 events => throughput is 5.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3541s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7067s [COUNTERS] OVERALL MEs ( 32 ) : 0.2884s for 16384 events => throughput is 5.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2126s - [COUNTERS] Fortran Other ( 0 ) : 0.0452s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5671s for 314106 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0402s for 16384 events => throughput is 4.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0618s for 314106 events => throughput is 5.08E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0240s + [COUNTERS] Fortran Other ( 0 ) : 0.0451s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3795s for 314106 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0403s for 16384 events => throughput is 4.07E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0619s for 314106 events => throughput is 5.08E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2883s for 16384 events => throughput is 5.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9243s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2883s for 16384 events => throughput is 5.68E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7360s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2956s - [COUNTERS] Fortran Other ( 0 ) : 0.0817s + [COUNTERS] PROGRAM TOTAL : 1.8234s + [COUNTERS] Fortran Other ( 0 ) : 0.0814s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4524s for 882930 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1088s for 16384 events => throughput is 1.51E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1286s for 882930 events => throughput is 6.86E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9815s for 882930 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1091s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1279s for 882930 events => throughput is 6.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2890s for 16384 events => throughput is 5.67E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0066s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2890s for 16384 events => throughput is 5.67E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2900s for 16384 events => throughput is 5.65E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5334s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2900s for 16384 events => throughput is 5.65E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0523s - [COUNTERS] Fortran Other ( 0 ) : 0.0344s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3397s for 187611 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0804s for 16384 events => throughput is 2.04E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9405s + [COUNTERS] Fortran Other ( 0 ) : 0.0345s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2281s for 187611 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0809s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0611s for 16384 events => throughput is 2.68E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0949s for 187611 events => throughput is 1.98E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0947s for 187611 events => throughput is 1.98E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2865s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7658s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2865s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2864s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6541s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2864s for 16384 events => throughput is 5.72E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6806s - [COUNTERS] Fortran Other ( 0 ) : 0.1365s + [COUNTERS] PROGRAM TOTAL : 2.7569s + [COUNTERS] Fortran Other ( 0 ) : 0.1355s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.7979s for 1696178 events => throughput is 6.06E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0873s for 16384 events => throughput is 1.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0828s for 16384 events => throughput is 1.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1430s for 1696178 events => throughput is 1.19E+07 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8740s for 1696178 events => throughput is 9.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0872s for 16384 events => throughput is 1.88E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0834s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1438s for 1696178 events => throughput is 1.18E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2860s for 16384 events => throughput is 5.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 3.3946s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2860s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4708s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9250s - [COUNTERS] Fortran Other ( 0 ) : 0.0318s + [COUNTERS] PROGRAM TOTAL : 0.8442s + [COUNTERS] Fortran Other ( 0 ) : 0.0312s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2679s for 138227 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0559s for 16384 events => throughput is 2.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0540s for 16384 events => throughput is 3.03E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0749s for 138227 events => throughput is 1.84E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1870s for 138227 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0541s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0751s for 138227 events => throughput is 1.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2857s for 16384 events => throughput is 5.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6393s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2857s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5581s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2861s for 16384 events => throughput is 5.73E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0281s - [COUNTERS] Fortran Other ( 0 ) : 0.0397s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3673s for 215899 events => throughput is 5.88E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0303s for 16384 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0663s for 215899 events => throughput is 3.26E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9157s + [COUNTERS] Fortran Other ( 0 ) : 0.0395s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2409s for 215899 events => throughput is 8.96E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0769s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0303s for 16384 events => throughput is 5.41E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0662s for 215899 events => throughput is 3.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2892s for 16384 events => throughput is 5.67E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7389s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2892s for 16384 events => throughput is 5.67E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3032s for 16384 events => throughput is 5.40E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6125s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3032s for 16384 events => throughput is 5.40E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0835s - [COUNTERS] Fortran Other ( 0 ) : 0.0384s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4908s for 254421 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0209s for 16384 events => throughput is 7.85E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0341s for 254421 events => throughput is 7.45E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] PROGRAM TOTAL : 0.9338s + [COUNTERS] Fortran Other ( 0 ) : 0.0388s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3406s for 254421 events => throughput is 7.47E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.86E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0340s for 254421 events => throughput is 7.48E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2898s for 16384 events => throughput is 5.65E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7938s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6440s [COUNTERS] OVERALL MEs ( 32 ) : 0.2898s for 16384 events => throughput is 5.65E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.6655s - [COUNTERS] Fortran Other ( 0 ) : 0.0872s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8364s for 1024423 events => throughput is 5.58E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0888s + [COUNTERS] Fortran Other ( 0 ) : 0.0870s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2634s for 1024423 events => throughput is 8.11E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0890s for 16384 events => throughput is 1.84E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1329s for 1024423 events => throughput is 7.71E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0862s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1326s for 1024423 events => throughput is 7.73E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2863s for 16384 events => throughput is 5.72E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3792s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2863s for 16384 events => throughput is 5.72E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2856s for 16384 events => throughput is 5.74E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8032s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2856s for 16384 events => throughput is 5.74E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9908s - [COUNTERS] Fortran Other ( 0 ) : 0.0368s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3329s for 193396 events => throughput is 5.81E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0945s for 16384 events => throughput is 1.73E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8771s + [COUNTERS] Fortran Other ( 0 ) : 0.0374s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2182s for 193396 events => throughput is 8.86E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0943s for 16384 events => throughput is 1.74E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0316s for 16384 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 193396 events => throughput is 3.23E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.16E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 193396 events => throughput is 3.22E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7029s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2880s for 16384 events => throughput is 5.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2883s for 16384 events => throughput is 5.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5888s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2883s for 16384 events => throughput is 5.68E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4399s - [COUNTERS] Fortran Other ( 0 ) : 0.0487s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6501s for 362054 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2231s + [COUNTERS] Fortran Other ( 0 ) : 0.0488s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4362s for 362054 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0562s for 16384 events => throughput is 2.91E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0960s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1491s for 362054 events => throughput is 2.43E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0961s for 16384 events => throughput is 1.71E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1452s for 362054 events => throughput is 2.49E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2858s for 16384 events => throughput is 5.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1541s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2858s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2857s for 16384 events => throughput is 5.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9374s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2857s for 16384 events => throughput is 5.73E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G76/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1601s - [COUNTERS] Fortran Other ( 0 ) : 0.0454s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4564s for 265638 events => throughput is 5.82E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0765s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0500s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0888s for 265638 events => throughput is 2.99E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0036s + [COUNTERS] Fortran Other ( 0 ) : 0.0451s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2991s for 265638 events => throughput is 8.88E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0770s for 16384 events => throughput is 2.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0503s for 16384 events => throughput is 3.26E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0889s for 265638 events => throughput is 2.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8724s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7159s [COUNTERS] OVERALL MEs ( 32 ) : 0.2877s for 16384 events => throughput is 5.69E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.0203 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 0.8655 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0096s - [COUNTERS] Fortran Other ( 0 ) : 0.0414s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4911s for 259134 events => throughput is 5.28E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0431s for 16384 events => throughput is 3.80E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0329s for 16384 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 259134 events => throughput is 5.41E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.8526s + [COUNTERS] Fortran Other ( 0 ) : 0.0412s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3364s for 259134 events => throughput is 7.70E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0676s for 49152 events => throughput is 7.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0426s for 16384 events => throughput is 3.85E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0316s for 16384 events => throughput is 5.18E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 259134 events => throughput is 5.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0032s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2061s for 16384 events => throughput is 7.95E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8035s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2061s for 16384 events => throughput is 7.95E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2058s for 16384 events => throughput is 7.96E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6468s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2058s for 16384 events => throughput is 7.96E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 2.9406 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 2.5060 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7141s - [COUNTERS] Fortran Other ( 0 ) : 0.0346s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3382s for 187490 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0678s for 16384 events => throughput is 2.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6044s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2298s for 187490 events => throughput is 8.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0673s for 16384 events => throughput is 2.43E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.09E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0168s for 187490 events => throughput is 1.12E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0079s for 16384 events => throughput is 2.08E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0166s for 187490 events => throughput is 1.13E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0030s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6148s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0990s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5054s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0990s for 16384 events => throughput is 1.65E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7927s - [COUNTERS] Fortran Other ( 0 ) : 0.0399s + [COUNTERS] PROGRAM TOTAL : 0.6591s + [COUNTERS] Fortran Other ( 0 ) : 0.0408s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4125s for 229909 events => throughput is 5.57E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2778s for 229909 events => throughput is 8.28E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0438s for 16384 events => throughput is 3.74E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0180s for 16384 events => throughput is 9.11E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0304s for 229909 events => throughput is 7.57E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.77E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0181s for 16384 events => throughput is 9.07E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0303s for 229909 events => throughput is 7.58E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6936s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5598s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7108s - [COUNTERS] Fortran Other ( 0 ) : 0.0335s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3241s for 170163 events => throughput is 5.25E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6121s + [COUNTERS] Fortran Other ( 0 ) : 0.0334s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2251s for 170163 events => throughput is 7.56E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0460s for 16384 events => throughput is 3.56E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0237s for 16384 events => throughput is 6.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0353s for 170163 events => throughput is 4.82E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0353s for 170163 events => throughput is 4.81E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6114s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5127s [COUNTERS] OVERALL MEs ( 32 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.6880s - [COUNTERS] Fortran Other ( 0 ) : 0.0321s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2832s for 155440 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0702s for 16384 events => throughput is 2.33E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.5948s + [COUNTERS] Fortran Other ( 0 ) : 0.0323s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1926s for 155440 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0696s for 16384 events => throughput is 2.35E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0206s for 16384 events => throughput is 7.96E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0311s for 155440 events => throughput is 5.01E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0030s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0309s for 155440 events => throughput is 5.02E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1019s for 16384 events => throughput is 1.61E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5861s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1019s for 16384 events => throughput is 1.61E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4956s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 4.6175 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 4.0887 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0623s - [COUNTERS] Fortran Other ( 0 ) : 0.0373s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3593s for 193303 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0801s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0046s for 16384 events => throughput is 3.56E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9512s + [COUNTERS] Fortran Other ( 0 ) : 0.0371s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2468s for 193303 events => throughput is 7.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0810s for 49152 events => throughput is 6.07E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0047s for 16384 events => throughput is 3.51E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0127s for 193303 events => throughput is 1.52E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4356s for 16384 events => throughput is 3.76E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6267s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4356s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4354s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5158s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4354s for 16384 events => throughput is 3.76E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G21/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4816s - [COUNTERS] Fortran Other ( 0 ) : 0.0533s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6807s for 430212 events => throughput is 6.32E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0800s for 49152 events => throughput is 6.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1012s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.47E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0333s for 430212 events => throughput is 1.29E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.2442s + [COUNTERS] Fortran Other ( 0 ) : 0.0530s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4438s for 430212 events => throughput is 9.69E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1016s for 16384 events => throughput is 1.61E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0332s for 430212 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4364s for 16384 events => throughput is 3.75E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0453s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4364s for 16384 events => throughput is 3.75E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4360s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8081s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4360s for 16384 events => throughput is 3.76E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0230s - [COUNTERS] Fortran Other ( 0 ) : 0.0322s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2870s for 154293 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0808s for 49152 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0099s for 16384 events => throughput is 1.65E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.56E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9319s + [COUNTERS] Fortran Other ( 0 ) : 0.0319s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1976s for 154293 events => throughput is 7.81E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0800s for 49152 events => throughput is 6.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0101s for 16384 events => throughput is 1.62E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4352s for 16384 events => throughput is 3.76E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5878s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4352s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4359s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4960s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4359s for 16384 events => throughput is 3.76E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0148s - [COUNTERS] Fortran Other ( 0 ) : 0.0317s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3184s for 159370 events => throughput is 5.01E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0797s for 49152 events => throughput is 6.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0053s for 16384 events => throughput is 3.06E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.23E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s + [COUNTERS] PROGRAM TOTAL : 0.9255s + [COUNTERS] Fortran Other ( 0 ) : 0.0312s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2254s for 159370 events => throughput is 7.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0057s for 16384 events => throughput is 2.86E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.22E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0033s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4355s for 16384 events => throughput is 3.76E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5793s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4355s for 16384 events => throughput is 3.76E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4394s for 16384 events => throughput is 3.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4861s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4394s for 16384 events => throughput is 3.73E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.4356 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.0251 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7918s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3851s for 212440 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0682s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 8.01E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0324s for 212440 events => throughput is 6.56E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.6663s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2603s for 212440 events => throughput is 8.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0686s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0202s for 16384 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.58E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6925s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0993s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5669s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8271s - [COUNTERS] Fortran Other ( 0 ) : 0.0411s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4552s for 250568 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0708s for 49152 events => throughput is 6.95E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.73E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6747s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3045s for 250568 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0431s for 16384 events => throughput is 3.80E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0126s for 16384 events => throughput is 1.30E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0241s for 250568 events => throughput is 1.04E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0032s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0130s for 16384 events => throughput is 1.26E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0242s for 250568 events => throughput is 1.03E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0030s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7277s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0994s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0990s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5758s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0990s for 16384 events => throughput is 1.66E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7888s + [COUNTERS] PROGRAM TOTAL : 0.6560s [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4131s for 227751 events => throughput is 5.51E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0677s for 16384 events => throughput is 2.42E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0061s for 16384 events => throughput is 2.67E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0157s for 227751 events => throughput is 1.45E+07 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2798s for 227751 events => throughput is 8.14E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0682s for 16384 events => throughput is 2.40E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0061s for 16384 events => throughput is 2.70E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.47E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0997s for 16384 events => throughput is 1.64E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6890s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0997s for 16384 events => throughput is 1.64E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0996s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5565s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0996s for 16384 events => throughput is 1.65E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.7556 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.6436 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7433s - [COUNTERS] Fortran Other ( 0 ) : 0.0327s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3568s for 184243 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0442s for 16384 events => throughput is 3.70E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0250s for 16384 events => throughput is 6.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0386s for 184243 events => throughput is 4.78E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0030s + [COUNTERS] PROGRAM TOTAL : 0.6329s + [COUNTERS] Fortran Other ( 0 ) : 0.0325s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2482s for 184243 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0436s for 16384 events => throughput is 3.76E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.59E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 184243 events => throughput is 4.86E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0985s for 16384 events => throughput is 1.66E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6448s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0985s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0984s for 16384 events => throughput is 1.67E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5345s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0984s for 16384 events => throughput is 1.67E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 2.4426 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 1.8292 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/G14/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4317s - [COUNTERS] Fortran Other ( 0 ) : 0.0981s + [COUNTERS] PROGRAM TOTAL : 1.8185s + [COUNTERS] Fortran Other ( 0 ) : 0.0968s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8684s for 1143085 events => throughput is 6.12E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2568s for 1143085 events => throughput is 9.10E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.15E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0567s for 16384 events => throughput is 2.89E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0110s for 16384 events => throughput is 1.49E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0433s for 1143085 events => throughput is 2.64E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0111s for 16384 events => throughput is 1.48E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0429s for 1143085 events => throughput is 2.66E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2065s for 16384 events => throughput is 7.93E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2251s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2065s for 16384 events => throughput is 7.93E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2067s for 16384 events => throughput is 7.93E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6118s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2067s for 16384 events => throughput is 7.93E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 4.3466 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 3.9256 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6152s - [COUNTERS] Fortran Other ( 0 ) : 0.0462s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6177s for 332018 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0528s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4215s + [COUNTERS] Fortran Other ( 0 ) : 0.0461s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4246s for 332018 events => throughput is 7.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0532s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0787s for 332018 events => throughput is 4.22E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0786s for 332018 events => throughput is 4.22E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6084s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0067s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6084s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6097s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8119s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6097s for 16384 events => throughput is 2.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3828s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3407s for 183011 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0629s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 183011 events => throughput is 1.84E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2750s + [COUNTERS] Fortran Other ( 0 ) : 0.0347s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2352s for 183011 events => throughput is 7.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0772s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0631s for 16384 events => throughput is 2.60E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0991s for 183011 events => throughput is 1.85E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6083s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7745s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6083s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6086s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6664s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6086s for 16384 events => throughput is 2.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3194s - [COUNTERS] Fortran Other ( 0 ) : 0.0370s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3487s for 193329 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2017s + [COUNTERS] Fortran Other ( 0 ) : 0.0369s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2325s for 193329 events => throughput is 8.31E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0610s for 193329 events => throughput is 3.17E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0356s for 16384 events => throughput is 4.60E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0608s for 193329 events => throughput is 3.18E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6085s for 16384 events => throughput is 2.69E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7109s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6085s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5936s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6081s for 16384 events => throughput is 2.69E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.8425 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.6998 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8318s - [COUNTERS] Fortran Other ( 0 ) : 0.0393s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0426s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4361s for 243014 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0670s for 49152 events => throughput is 7.33E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0443s for 16384 events => throughput is 3.70E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6876s + [COUNTERS] Fortran Other ( 0 ) : 0.0388s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2943s for 243014 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0669s for 49152 events => throughput is 7.35E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.77E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0259s for 16384 events => throughput is 6.33E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 243014 events => throughput is 5.90E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0411s for 243014 events => throughput is 5.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7332s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5890s [COUNTERS] OVERALL MEs ( 32 ) : 0.0986s for 16384 events => throughput is 1.66E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.5489 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.3929 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7728s - [COUNTERS] Fortran Other ( 0 ) : 0.0311s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2752s for 152585 events => throughput is 5.54E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6853s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1864s for 152585 events => throughput is 8.19E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0799s for 49152 events => throughput is 6.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0048s for 16384 events => throughput is 3.42E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0049s for 16384 events => throughput is 3.36E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0122s for 152585 events => throughput is 1.25E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2093s for 16384 events => throughput is 7.83E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5635s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2093s for 16384 events => throughput is 7.83E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2103s for 16384 events => throughput is 7.79E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4750s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2103s for 16384 events => throughput is 7.79E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G62/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7555s - [COUNTERS] Fortran Other ( 0 ) : 0.0290s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2218s for 121146 events => throughput is 5.46E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6869s + [COUNTERS] Fortran Other ( 0 ) : 0.0295s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1510s for 121146 events => throughput is 8.02E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0798s for 49152 events => throughput is 6.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0836s for 16384 events => throughput is 1.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 7.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 121146 events => throughput is 3.75E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0844s for 16384 events => throughput is 1.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0207s for 16384 events => throughput is 7.91E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 121146 events => throughput is 3.77E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0034s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2092s for 16384 events => throughput is 7.83E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5463s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2092s for 16384 events => throughput is 7.83E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2098s for 16384 events => throughput is 7.81E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4771s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2098s for 16384 events => throughput is 7.81E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 1.6630 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 1.4659 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6511s - [COUNTERS] Fortran Other ( 0 ) : 0.0427s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0431s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6558s for 329671 events => throughput is 5.03E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4550s + [COUNTERS] Fortran Other ( 0 ) : 0.0416s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4633s for 329671 events => throughput is 7.12E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0509s for 16384 events => throughput is 3.22E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0814s for 329671 events => throughput is 4.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0505s for 16384 events => throughput is 3.24E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0811s for 329671 events => throughput is 4.06E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.6058s for 16384 events => throughput is 2.70E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0453s - [COUNTERS] OVERALL MEs ( 32 ) : 0.6058s for 16384 events => throughput is 2.70E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6054s for 16384 events => throughput is 2.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8497s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6054s for 16384 events => throughput is 2.71E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.9311 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.7824 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/G7/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9198s - [COUNTERS] Fortran Other ( 0 ) : 0.0400s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4908s for 255151 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.90E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0417s for 16384 events => throughput is 3.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0511s for 255151 events => throughput is 4.99E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7717s + [COUNTERS] Fortran Other ( 0 ) : 0.0399s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3436s for 255151 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0827s for 81920 events => throughput is 9.91E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0416s for 16384 events => throughput is 3.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0508s for 255151 events => throughput is 5.02E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1005s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8193s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1005s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0999s for 16384 events => throughput is 1.64E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6718s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0999s for 16384 events => throughput is 1.64E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.4160 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.2040 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.6386s - [COUNTERS] Fortran Other ( 0 ) : 0.0341s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2931s for 159224 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0442s for 16384 events => throughput is 3.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.97E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.5427s + [COUNTERS] Fortran Other ( 0 ) : 0.0338s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1975s for 159224 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0056s for 16384 events => throughput is 2.92E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0133s for 159224 events => throughput is 1.20E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0987s for 16384 events => throughput is 1.66E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5400s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0987s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4436s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0991s for 16384 events => throughput is 1.65E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7587s - [COUNTERS] Fortran Other ( 0 ) : 0.0347s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3900s for 201854 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.83E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0166s for 16384 events => throughput is 9.90E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.31E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.6427s + [COUNTERS] Fortran Other ( 0 ) : 0.0341s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2738s for 201854 events => throughput is 7.37E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0165s for 16384 events => throughput is 9.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.32E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.0982s for 16384 events => throughput is 1.67E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6605s - [COUNTERS] OVERALL MEs ( 32 ) : 0.0982s for 16384 events => throughput is 1.67E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.0985s for 16384 events => throughput is 1.66E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5442s + [COUNTERS] OVERALL MEs ( 32 ) : 0.0985s for 16384 events => throughput is 1.66E+05 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 0.9817 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 0.8244 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9711s + [COUNTERS] PROGRAM TOTAL : 0.8134s [COUNTERS] Fortran Other ( 0 ) : 0.0426s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4984s for 268443 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0094s for 16384 events => throughput is 1.74E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3420s for 268443 events => throughput is 7.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0093s for 16384 events => throughput is 1.76E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0204s for 268443 events => throughput is 1.31E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2081s for 16384 events => throughput is 7.87E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7629s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2081s for 16384 events => throughput is 7.87E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2072s for 16384 events => throughput is 7.91E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6063s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2072s for 16384 events => throughput is 7.91E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.7937 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.6974 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7830s + [COUNTERS] PROGRAM TOTAL : 0.6869s [COUNTERS] Fortran Other ( 0 ) : 0.0329s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3141s for 168484 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0661s for 16384 events => throughput is 2.48E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 4.89E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.57E+07 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2174s for 168484 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0660s for 16384 events => throughput is 2.48E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0034s for 16384 events => throughput is 4.88E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.58E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0031s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.2069s for 16384 events => throughput is 7.92E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5761s - [COUNTERS] OVERALL MEs ( 32 ) : 0.2069s for 16384 events => throughput is 7.92E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.2071s for 16384 events => throughput is 7.91E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4797s + [COUNTERS] OVERALL MEs ( 32 ) : 0.2071s for 16384 events => throughput is 7.91E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 156.9428 seconds -__CUDACPP_DEBUG: gen_ximprove.launch finished in 157.5067 seconds -__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 157.5074 seconds +__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 131.8907 seconds +__CUDACPP_DEBUG: gen_ximprove.launch finished in 132.4511 seconds +__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 132.4516 seconds __CUDACPP_DEBUG: GridPackCmd.launch (3a) combine_events combine_events __CUDACPP_DEBUG: GridPackCmd.launch (3b) store_events @@ -2116,9 +2116,9 @@ store_events INFO: No version of lhapdf. Can not run systematics computation decay_events -from_cards -__CUDACPP_DEBUG: GridPackCmd.launch finished in 160.1718 seconds +__CUDACPP_DEBUG: GridPackCmd.launch finished in 135.1144 seconds __CUDACPP_DEBUG: GridPackCmd.__init__ back from self.launch DONE write ./events.lhe.gz -END: Thu Aug 22 04:01:19 PM CEST 2024 -ELAPSED: 160 seconds +END: Thu Aug 22 05:13:53 PM CEST 2024 +ELAPSED: 135 seconds diff --git a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppavx2/output.txt b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppavx2/output.txt index 807974359c..0054a57b91 100644 --- a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppavx2/output.txt +++ b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppavx2/output.txt @@ -1,91 +1,91 @@ -START: Thu Aug 22 03:51:53 PM CEST 2024 +START: Thu Aug 22 05:05:42 PM CEST 2024 On itgold91.cern.ch [CPU: Intel(R) Xeon(R) Gold 6326 CPU (nproc=32)] [GPU: none]: CUDACPP_RUNTIME_DISABLEFPE is set -CUDACPP_RUNTIME_SKIPXBINCHECKS is not set -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:51 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +CUDACPP_RUNTIME_SKIPXBINCHECKS is set +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:05 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.avx2_m_inl0_hrd0/madevent_cpp Now generating 100 events with random seed 21 and granularity 1 ************************************************************ * * @@ -211,1900 +211,1900 @@ __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event starting INFO: need to improve 108 channels __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 19.5854 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 17.3847 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2312s - [COUNTERS] Fortran Other ( 0 ) : 0.0334s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3224s for 176708 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1273s + [COUNTERS] Fortran Other ( 0 ) : 0.0341s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2190s for 176708 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0774s for 16384 events => throughput is 2.12E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0463s for 16384 events => throughput is 3.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0685s for 176708 events => throughput is 2.58E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0684s for 176708 events => throughput is 2.58E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5245s for 16384 events => throughput is 3.12E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7067s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5245s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5243s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6029s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5243s for 16384 events => throughput is 3.12E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4511s - [COUNTERS] Fortran Other ( 0 ) : 0.0471s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6074s for 337001 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2503s + [COUNTERS] Fortran Other ( 0 ) : 0.0468s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4068s for 337001 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0215s for 16384 events => throughput is 7.61E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0377s for 337001 events => throughput is 8.94E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0217s for 16384 events => throughput is 7.56E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0376s for 337001 events => throughput is 8.95E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9244s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7234s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3203s - [COUNTERS] Fortran Other ( 0 ) : 0.0356s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3551s for 196960 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0671s for 16384 events => throughput is 2.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1032s for 196960 events => throughput is 1.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 1.2062s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2398s for 196960 events => throughput is 8.21E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0670s for 16384 events => throughput is 2.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1031s for 196960 events => throughput is 1.91E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5235s for 16384 events => throughput is 3.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7968s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5235s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5237s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6825s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5237s for 16384 events => throughput is 3.13E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5043s - [COUNTERS] Fortran Other ( 0 ) : 0.0426s + [COUNTERS] PROGRAM TOTAL : 1.3162s + [COUNTERS] Fortran Other ( 0 ) : 0.0420s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6295s for 324156 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4427s for 324156 events => throughput is 7.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0528s for 16384 events => throughput is 3.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0382s for 16384 events => throughput is 4.29E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 324156 events => throughput is 5.82E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5262s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9780s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5262s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7894s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1826s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3042s for 176248 events => throughput is 5.79E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0697s for 49152 events => throughput is 7.05E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0806s for 16384 events => throughput is 2.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0297s for 16384 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0581s for 176248 events => throughput is 3.03E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] PROGRAM TOTAL : 1.0761s + [COUNTERS] Fortran Other ( 0 ) : 0.0357s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2000s for 176248 events => throughput is 8.81E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0804s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0295s for 16384 events => throughput is 5.56E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0575s for 176248 events => throughput is 3.06E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5243s for 16384 events => throughput is 3.12E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6583s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5243s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5244s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5517s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5244s for 16384 events => throughput is 3.12E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1028s - [COUNTERS] Fortran Other ( 0 ) : 0.0310s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2508s for 128162 events => throughput is 5.11E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0267s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1735s for 128162 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0773s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0541s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0499s for 128162 events => throughput is 2.57E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0504s for 128162 events => throughput is 2.54E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5242s for 16384 events => throughput is 3.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5786s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5025s [COUNTERS] OVERALL MEs ( 32 ) : 0.5242s for 16384 events => throughput is 3.13E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G2/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1260s - [COUNTERS] Fortran Other ( 0 ) : 0.0675s + [COUNTERS] PROGRAM TOTAL : 1.7636s + [COUNTERS] Fortran Other ( 0 ) : 0.0671s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2194s for 680231 events => throughput is 5.58E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8585s for 680231 events => throughput is 7.92E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0850s for 16384 events => throughput is 1.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.80E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0482s for 680231 events => throughput is 1.41E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5241s for 16384 events => throughput is 3.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6019s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5241s for 16384 events => throughput is 3.13E+04 events/s -/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log - [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2948s - [COUNTERS] Fortran Other ( 0 ) : 0.0400s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3891s for 227876 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0764s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0844s for 16384 events => throughput is 1.94E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0729s for 227876 events => throughput is 3.13E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0483s for 680231 events => throughput is 1.41E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5238s for 16384 events => throughput is 3.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7710s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2398s [COUNTERS] OVERALL MEs ( 32 ) : 0.5238s for 16384 events => throughput is 3.13E+04 events/s +/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log + [COUNTERS] *** USING RDTSC-BASED TIMERS *** + [COUNTERS] PROGRAM TOTAL : 1.1581s + [COUNTERS] Fortran Other ( 0 ) : 0.0408s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2535s for 227876 events => throughput is 8.99E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0760s for 16384 events => throughput is 2.16E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0335s for 16384 events => throughput is 4.89E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 227876 events => throughput is 3.14E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5241s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6341s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5241s for 16384 events => throughput is 3.13E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3391s - [COUNTERS] Fortran Other ( 0 ) : 0.0391s + [COUNTERS] PROGRAM TOTAL : 1.1872s + [COUNTERS] Fortran Other ( 0 ) : 0.0396s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5013s for 258529 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0519s for 16384 events => throughput is 3.16E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.76E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0387s for 258529 events => throughput is 6.68E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3488s for 258529 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.80E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0383s for 258529 events => throughput is 6.75E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5257s for 16384 events => throughput is 3.12E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8133s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5257s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5263s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6610s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5263s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G75/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4538s - [COUNTERS] Fortran Other ( 0 ) : 0.0438s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5303s for 288195 events => throughput is 5.43E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2761s + [COUNTERS] Fortran Other ( 0 ) : 0.0435s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3540s for 288195 events => throughput is 8.14E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.81E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0817s for 288195 events => throughput is 3.53E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9264s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5260s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7501s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5260s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7339s - [COUNTERS] Fortran Other ( 0 ) : 0.0488s + [COUNTERS] PROGRAM TOTAL : 1.5097s + [COUNTERS] Fortran Other ( 0 ) : 0.0492s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6603s for 362045 events => throughput is 5.48E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4354s for 362045 events => throughput is 8.31E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0636s for 16384 events => throughput is 2.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0635s for 16384 events => throughput is 2.58E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1096s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1707s for 362045 events => throughput is 2.12E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1709s for 362045 events => throughput is 2.12E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5232s for 16384 events => throughput is 3.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2107s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5232s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5235s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9862s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5235s for 16384 events => throughput is 3.13E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2345s - [COUNTERS] Fortran Other ( 0 ) : 0.0395s + [COUNTERS] PROGRAM TOTAL : 1.1181s + [COUNTERS] Fortran Other ( 0 ) : 0.0401s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3288s for 203191 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2083s for 203191 events => throughput is 9.76E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0368s for 16384 events => throughput is 4.45E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0371s for 16384 events => throughput is 4.42E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 203191 events => throughput is 3.02E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5262s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7083s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5262s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5908s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1646s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3783s for 205739 events => throughput is 5.44E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0383s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2543s for 205739 events => throughput is 8.09E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0058s for 16384 events => throughput is 2.83E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0058s for 16384 events => throughput is 2.85E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.42E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5244s for 16384 events => throughput is 3.12E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6401s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5244s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5242s for 16384 events => throughput is 3.13E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5141s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5242s for 16384 events => throughput is 3.13E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3237s - [COUNTERS] Fortran Other ( 0 ) : 0.0395s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3660s for 214038 events => throughput is 5.85E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2116s + [COUNTERS] Fortran Other ( 0 ) : 0.0389s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2394s for 214038 events => throughput is 8.94E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0670s for 214038 events => throughput is 3.19E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5867s for 16384 events => throughput is 2.79E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7370s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5867s for 16384 events => throughput is 2.79E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.6036s for 16384 events => throughput is 2.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6080s + [COUNTERS] OVERALL MEs ( 32 ) : 0.6036s for 16384 events => throughput is 2.71E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 4.6503 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 4.1274 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6852s - [COUNTERS] Fortran Other ( 0 ) : 0.0492s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6191s for 344023 events => throughput is 5.56E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4568s + [COUNTERS] Fortran Other ( 0 ) : 0.0490s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4135s for 344023 events => throughput is 8.32E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0835s for 81920 events => throughput is 9.81E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0580s for 16384 events => throughput is 2.83E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1011s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1457s for 344023 events => throughput is 2.36E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0564s for 16384 events => throughput is 2.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1008s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1453s for 344023 events => throughput is 2.37E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5488s for 16384 events => throughput is 2.99E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1364s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5488s for 16384 events => throughput is 2.99E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9288s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G43/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4244s - [COUNTERS] Fortran Other ( 0 ) : 0.0394s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4131s for 214181 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1352s for 212992 events => throughput is 1.58E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0712s for 16384 events => throughput is 2.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0995s for 214181 events => throughput is 2.15E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2988s + [COUNTERS] Fortran Other ( 0 ) : 0.0388s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2861s for 214181 events => throughput is 7.49E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1359s for 212992 events => throughput is 1.57E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0590s for 16384 events => throughput is 2.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0714s for 16384 events => throughput is 2.29E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 214181 events => throughput is 2.16E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8964s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5281s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7707s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5281s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5125s - [COUNTERS] Fortran Other ( 0 ) : 0.0423s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5404s for 279555 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1130s for 147456 events => throughput is 1.30E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0591s for 16384 events => throughput is 2.77E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0620s for 16384 events => throughput is 2.64E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0879s for 279555 events => throughput is 3.18E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] PROGRAM TOTAL : 1.3431s + [COUNTERS] Fortran Other ( 0 ) : 0.0419s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3752s for 279555 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1131s for 147456 events => throughput is 1.30E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0572s for 16384 events => throughput is 2.86E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0618s for 16384 events => throughput is 2.65E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0869s for 279555 events => throughput is 3.22E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5278s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9847s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5278s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8156s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 2.1005 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 1.8695 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/G67/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0889s - [COUNTERS] Fortran Other ( 0 ) : 0.0754s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2786s for 814370 events => throughput is 6.37E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8569s + [COUNTERS] Fortran Other ( 0 ) : 0.2877s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8359s for 814370 events => throughput is 9.74E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0794s for 49152 events => throughput is 6.19E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1111s for 16384 events => throughput is 1.47E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0304s for 16384 events => throughput is 5.39E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1102s for 16384 events => throughput is 1.49E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0306s for 16384 events => throughput is 5.35E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0592s for 814370 events => throughput is 1.38E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3742s for 16384 events => throughput is 4.38E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7147s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3742s for 16384 events => throughput is 4.38E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3738s for 16384 events => throughput is 4.38E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4831s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3738s for 16384 events => throughput is 4.38E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 11.4394 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 10.2448 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2086s - [COUNTERS] Fortran Other ( 0 ) : 0.0815s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5459s for 933480 events => throughput is 6.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 49152 events => throughput is 6.33E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1060s for 16384 events => throughput is 1.55E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1002s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1597s for 933480 events => throughput is 5.85E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.7127s + [COUNTERS] Fortran Other ( 0 ) : 0.0807s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0492s for 933480 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1018s for 16384 events => throughput is 1.61E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1003s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1612s for 933480 events => throughput is 5.79E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0578s for 16384 events => throughput is 1.55E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1507s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0578s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0615s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6512s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0615s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9686s - [COUNTERS] Fortran Other ( 0 ) : 0.0513s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4224s for 226350 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8236s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2922s for 226350 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0766s for 16384 events => throughput is 2.14E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1221s for 226350 events => throughput is 1.85E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1222s for 226350 events => throughput is 1.85E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0582s for 16384 events => throughput is 1.55E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9104s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0582s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0584s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7651s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0584s for 16384 events => throughput is 1.55E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1160s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6508s for 323984 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0506s for 16384 events => throughput is 3.24E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9357s + [COUNTERS] Fortran Other ( 0 ) : 0.0532s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4588s for 323984 events => throughput is 7.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0500s for 16384 events => throughput is 3.28E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0635s for 16384 events => throughput is 2.58E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0931s for 323984 events => throughput is 3.48E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0582s for 16384 events => throughput is 1.55E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0578s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0582s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0587s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8770s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0587s for 16384 events => throughput is 1.55E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1865s - [COUNTERS] Fortran Other ( 0 ) : 0.0424s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7133s for 355559 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0502s for 16384 events => throughput is 3.27E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9658s + [COUNTERS] Fortran Other ( 0 ) : 0.0422s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5026s for 355559 events => throughput is 7.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0501s for 16384 events => throughput is 3.27E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0623s for 16384 events => throughput is 2.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0930s for 355559 events => throughput is 3.82E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0929s for 355559 events => throughput is 3.83E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0679s for 16384 events => throughput is 1.53E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1186s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0679s for 16384 events => throughput is 1.53E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0578s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9080s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0578s for 16384 events => throughput is 1.55E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G92/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9148s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4549s for 255849 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.32E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0386s for 16384 events => throughput is 4.24E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0837s for 255849 events => throughput is 3.06E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 1.7627s + [COUNTERS] Fortran Other ( 0 ) : 0.0410s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3045s for 255849 events => throughput is 8.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.33E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0782s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0388s for 16384 events => throughput is 4.23E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0838s for 255849 events => throughput is 3.05E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0586s for 16384 events => throughput is 1.55E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8562s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0586s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0585s for 16384 events => throughput is 1.55E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7041s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0585s for 16384 events => throughput is 1.55E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 11.2420 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 9.5580 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9753s - [COUNTERS] Fortran Other ( 0 ) : 0.0781s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0453s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4090s for 859290 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1078s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.73E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0577s for 16384 events => throughput is 2.84E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0981s for 859290 events => throughput is 8.76E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.5281s + [COUNTERS] Fortran Other ( 0 ) : 0.0790s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9660s for 859290 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1061s for 16384 events => throughput is 1.54E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0575s for 16384 events => throughput is 2.85E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 859290 events => throughput is 8.65E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0645s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9108s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0645s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0640s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4641s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0640s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2382s - [COUNTERS] Fortran Other ( 0 ) : 0.0928s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.7906s for 1098402 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.6582s + [COUNTERS] Fortran Other ( 0 ) : 0.0914s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2111s for 1098402 events => throughput is 9.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0790s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0124s for 16384 events => throughput is 1.32E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.55E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.56E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0646s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1736s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0646s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0648s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5935s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0648s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2099s - [COUNTERS] Fortran Other ( 0 ) : 0.0448s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7486s for 378380 events => throughput is 5.05E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0561s for 16384 events => throughput is 2.92E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0849s for 378380 events => throughput is 4.46E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9883s + [COUNTERS] Fortran Other ( 0 ) : 0.0444s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5271s for 378380 events => throughput is 7.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0846s for 378380 events => throughput is 4.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0654s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1445s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0654s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9227s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G65/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7820s - [COUNTERS] Fortran Other ( 0 ) : 0.0735s + [COUNTERS] PROGRAM TOTAL : 2.3460s + [COUNTERS] Fortran Other ( 0 ) : 0.0727s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3550s for 819579 events => throughput is 6.05E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0146s for 16384 events => throughput is 1.12E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0396s for 819579 events => throughput is 2.07E+07 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9205s for 819579 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0147s for 16384 events => throughput is 1.12E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0390s for 819579 events => throughput is 2.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0701s for 16384 events => throughput is 1.53E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7119s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0701s for 16384 events => throughput is 1.53E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0702s for 16384 events => throughput is 1.53E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2757s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0702s for 16384 events => throughput is 1.53E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.4710 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 1.2749 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4593s - [COUNTERS] Fortran Other ( 0 ) : 0.0443s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6360s for 330261 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0876s for 81920 events => throughput is 9.35E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0570s for 16384 events => throughput is 2.87E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.89E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0075s for 16384 events => throughput is 2.20E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0198s for 330261 events => throughput is 1.67E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.2639s + [COUNTERS] Fortran Other ( 0 ) : 0.0432s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4440s for 330261 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0866s for 81920 events => throughput is 9.46E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0073s for 16384 events => throughput is 2.24E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0196s for 330261 events => throughput is 1.68E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5274s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9319s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5274s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5277s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7362s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5277s for 16384 events => throughput is 3.10E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 2.3316 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 1.8172 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3206s - [COUNTERS] Fortran Other ( 0 ) : 0.0833s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4474s for 919173 events => throughput is 6.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0841s for 16384 events => throughput is 1.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1318s for 919173 events => throughput is 6.97E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.8065s + [COUNTERS] Fortran Other ( 0 ) : 0.0828s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9350s for 919173 events => throughput is 9.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0837s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1332s for 919173 events => throughput is 6.90E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3464s for 16384 events => throughput is 4.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9742s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3464s for 16384 events => throughput is 4.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3461s for 16384 events => throughput is 4.73E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4604s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3461s for 16384 events => throughput is 4.73E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 13.7884 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 11.3546 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2070s - [COUNTERS] Fortran Other ( 0 ) : 0.0319s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2774s for 142763 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0768s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0562s for 16384 events => throughput is 2.92E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1224s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1941s for 142763 events => throughput is 7.36E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0650s for 16384 events => throughput is 2.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0902s for 142763 events => throughput is 1.58E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0899s for 142763 events => throughput is 1.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5298s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6772s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5298s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5301s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5923s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5301s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0173s - [COUNTERS] Fortran Other ( 0 ) : 0.0973s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8445s for 1119813 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1100s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1080s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1710s for 1119813 events => throughput is 6.55E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.4203s + [COUNTERS] Fortran Other ( 0 ) : 0.0964s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0427s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2487s for 1119813 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1097s for 16384 events => throughput is 1.49E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1078s for 16384 events => throughput is 1.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1705s for 1119813 events => throughput is 6.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5306s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4867s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5306s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8906s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1773s - [COUNTERS] Fortran Other ( 0 ) : 0.1097s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2210s for 1357398 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0869s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0174s for 16384 events => throughput is 9.40E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0556s for 1357398 events => throughput is 2.44E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.4422s + [COUNTERS] Fortran Other ( 0 ) : 0.1086s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4883s for 1357398 events => throughput is 9.12E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0867s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0174s for 16384 events => throughput is 9.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0554s for 1357398 events => throughput is 2.45E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5299s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6474s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5299s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9126s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7873s - [COUNTERS] Fortran Other ( 0 ) : 0.0533s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7183s for 398526 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5429s + [COUNTERS] Fortran Other ( 0 ) : 0.0518s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4798s for 398526 events => throughput is 8.31E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.20E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1145s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1655s for 398526 events => throughput is 2.41E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1644s for 398526 events => throughput is 2.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5326s for 16384 events => throughput is 3.08E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2546s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5326s for 16384 events => throughput is 3.08E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0133s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G53/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1378s - [COUNTERS] Fortran Other ( 0 ) : 0.0907s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9682s for 1103762 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0858s for 16384 events => throughput is 1.91E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1206s for 16384 events => throughput is 1.36E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1838s for 1103762 events => throughput is 6.01E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 2.5284s + [COUNTERS] Fortran Other ( 0 ) : 0.0903s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3623s for 1103762 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0767s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0862s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1204s for 16384 events => throughput is 1.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1830s for 1103762 events => throughput is 6.03E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5321s for 16384 events => throughput is 3.08E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6058s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5321s for 16384 events => throughput is 3.08E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5300s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9984s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5300s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4095s - [COUNTERS] Fortran Other ( 0 ) : 0.0441s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4659s for 272273 events => throughput is 5.84E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0598s for 16384 events => throughput is 2.74E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2469s + [COUNTERS] Fortran Other ( 0 ) : 0.0442s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3055s for 272273 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0585s for 16384 events => throughput is 2.80E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1099s for 272273 events => throughput is 2.48E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8811s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1092s for 272273 events => throughput is 2.49E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5282s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7186s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5282s for 16384 events => throughput is 3.10E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 1.2867 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 1.2210 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/G71/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2747s - [COUNTERS] Fortran Other ( 0 ) : 0.0290s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2208s for 109714 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0821s for 49152 events => throughput is 5.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0167s for 16384 events => throughput is 9.79E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2096s + [COUNTERS] Fortran Other ( 0 ) : 0.0286s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1572s for 109714 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0815s for 49152 events => throughput is 6.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0556s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0168s for 16384 events => throughput is 9.78E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.39E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7665s for 16384 events => throughput is 2.14E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5082s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7665s for 16384 events => throughput is 2.14E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7658s for 16384 events => throughput is 2.14E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4439s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7658s for 16384 events => throughput is 2.14E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.1633 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 1.6541 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1507s - [COUNTERS] Fortran Other ( 0 ) : 0.0881s + [COUNTERS] PROGRAM TOTAL : 1.6431s + [COUNTERS] Fortran Other ( 0 ) : 0.0859s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4825s for 949349 events => throughput is 6.40E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9778s for 949349 events => throughput is 9.71E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0650s for 16384 events => throughput is 2.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 949349 events => throughput is 8.73E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1093s for 949349 events => throughput is 8.69E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1704s for 16384 events => throughput is 9.61E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9803s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1704s for 16384 events => throughput is 9.61E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1692s for 16384 events => throughput is 9.68E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4739s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1692s for 16384 events => throughput is 9.68E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 6.1675 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 5.6523 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8257s - [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] PROGRAM TOTAL : 1.7194s + [COUNTERS] Fortran Other ( 0 ) : 0.0351s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3392s for 181152 events => throughput is 5.34E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2333s for 181152 events => throughput is 7.77E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0774s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0589s for 16384 events => throughput is 2.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0908s for 181152 events => throughput is 2.00E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0905s for 181152 events => throughput is 2.00E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0651s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7606s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0651s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0666s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6528s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0666s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0589s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5871s for 293756 events => throughput is 5.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0519s for 16384 events => throughput is 3.16E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8869s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4150s for 293756 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0658s for 16384 events => throughput is 2.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0922s for 293756 events => throughput is 3.19E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0923s for 293756 events => throughput is 3.18E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0624s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9965s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0624s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0621s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8248s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0621s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2542s - [COUNTERS] Fortran Other ( 0 ) : 0.0518s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7560s for 405834 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0175s + [COUNTERS] Fortran Other ( 0 ) : 0.0516s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5183s for 405834 events => throughput is 7.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0743s for 16384 events => throughput is 2.20E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 405834 events => throughput is 3.73E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1089s for 405834 events => throughput is 3.73E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0619s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1922s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0619s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0623s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9553s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0623s for 16384 events => throughput is 1.54E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 18.7386 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 16.5765 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0159s - [COUNTERS] Fortran Other ( 0 ) : 0.0769s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4119s for 847188 events => throughput is 6.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1029s for 16384 events => throughput is 1.59E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.5830s + [COUNTERS] Fortran Other ( 0 ) : 0.0764s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9796s for 847188 events => throughput is 8.65E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1031s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1229s for 847188 events => throughput is 6.89E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1225s for 847188 events => throughput is 6.92E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0662s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9496s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0662s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0663s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5167s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0663s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7578s - [COUNTERS] Fortran Other ( 0 ) : 0.0330s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3148s for 167274 events => throughput is 5.31E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6603s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2180s for 167274 events => throughput is 7.67E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0814s for 16384 events => throughput is 2.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0449s for 16384 events => throughput is 3.65E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0635s for 167274 events => throughput is 2.64E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0799s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0450s for 16384 events => throughput is 3.64E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0634s for 167274 events => throughput is 2.64E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0640s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6938s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0640s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0652s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5951s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0652s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3695s - [COUNTERS] Fortran Other ( 0 ) : 0.0989s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8849s for 1150245 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.7500s + [COUNTERS] Fortran Other ( 0 ) : 0.0970s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2690s for 1150245 events => throughput is 9.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0256s for 16384 events => throughput is 6.39E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0606s for 1150245 events => throughput is 1.90E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0598s for 1150245 events => throughput is 1.92E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3046s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0650s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6851s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0650s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0622s - [COUNTERS] Fortran Other ( 0 ) : 0.0477s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6582s for 355348 events => throughput is 5.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0298s for 16384 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0481s for 355348 events => throughput is 7.39E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s + [COUNTERS] PROGRAM TOTAL : 1.8543s + [COUNTERS] Fortran Other ( 0 ) : 0.0479s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4531s for 355348 events => throughput is 7.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0296s for 16384 events => throughput is 5.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 355348 events => throughput is 7.43E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0689s for 16384 events => throughput is 1.53E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9933s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0689s for 16384 events => throughput is 1.53E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0666s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7877s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0666s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0306s - [COUNTERS] Fortran Other ( 0 ) : 0.0785s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4157s for 864266 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1077s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1290s for 864266 events => throughput is 6.70E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.5755s + [COUNTERS] Fortran Other ( 0 ) : 0.0782s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0429s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9641s for 864266 events => throughput is 8.96E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1058s for 16384 events => throughput is 1.55E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1280s for 864266 events => throughput is 6.75E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0642s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9664s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0642s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0635s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5121s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0635s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0218s - [COUNTERS] Fortran Other ( 0 ) : 0.0405s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5657s for 285525 events => throughput is 5.05E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8534s + [COUNTERS] Fortran Other ( 0 ) : 0.0402s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4016s for 285525 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0587s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0821s for 285525 events => throughput is 3.48E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9569s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0802s for 285525 events => throughput is 3.56E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0631s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7902s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0631s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7583s - [COUNTERS] Fortran Other ( 0 ) : 0.0371s + [COUNTERS] PROGRAM TOTAL : 1.6461s + [COUNTERS] Fortran Other ( 0 ) : 0.0373s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3395s for 189666 events => throughput is 5.59E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0822s for 16384 events => throughput is 1.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0299s for 16384 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0540s for 189666 events => throughput is 3.51E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2288s for 189666 events => throughput is 8.29E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0821s for 16384 events => throughput is 2.00E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0300s for 16384 events => throughput is 5.46E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0533s for 189666 events => throughput is 3.56E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0669s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6914s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0669s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0661s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5800s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0661s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6557s - [COUNTERS] Fortran Other ( 0 ) : 0.0311s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2490s for 124553 events => throughput is 5.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.88E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0588s for 124553 events => throughput is 2.12E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s + [COUNTERS] PROGRAM TOTAL : 1.5838s + [COUNTERS] Fortran Other ( 0 ) : 0.0307s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1767s for 124553 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0754s for 81920 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.87E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0590s for 124553 events => throughput is 2.11E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0639s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5918s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0639s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0655s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5183s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0655s for 16384 events => throughput is 1.54E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 3.1919 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 2.7981 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G48/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5782s - [COUNTERS] Fortran Other ( 0 ) : 0.0447s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5793s for 318589 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0875s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1290s for 318589 events => throughput is 2.47E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.3844s + [COUNTERS] Fortran Other ( 0 ) : 0.0441s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3845s for 318589 events => throughput is 8.29E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 49152 events => throughput is 6.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0878s for 16384 events => throughput is 1.87E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1292s for 318589 events => throughput is 2.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5276s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0506s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5276s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8560s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5941s - [COUNTERS] Fortran Other ( 0 ) : 0.0435s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6627s for 343552 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0537s for 16384 events => throughput is 3.05E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3928s + [COUNTERS] Fortran Other ( 0 ) : 0.0431s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4610s for 343552 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0604s for 16384 events => throughput is 2.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0879s for 343552 events => throughput is 3.91E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0605s for 16384 events => throughput is 2.71E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0877s for 343552 events => throughput is 3.92E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0657s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5304s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8624s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5304s for 16384 events => throughput is 3.09E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 10.9393 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 9.3967 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3795s + [COUNTERS] PROGRAM TOTAL : 1.2538s [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4021s for 223142 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1097s for 223142 events => throughput is 2.03E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0045s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2711s for 223142 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0697s for 16384 events => throughput is 2.35E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1109s for 223142 events => throughput is 2.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8526s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5274s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7263s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5274s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5520s - [COUNTERS] Fortran Other ( 0 ) : 0.0419s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6259s for 323723 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3615s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4348s for 323723 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0601s for 16384 events => throughput is 2.73E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0865s for 323723 events => throughput is 3.74E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0863s for 323723 events => throughput is 3.75E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0254s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8347s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4240s - [COUNTERS] Fortran Other ( 0 ) : 0.0376s + [COUNTERS] PROGRAM TOTAL : 1.2835s + [COUNTERS] Fortran Other ( 0 ) : 0.0375s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4383s for 243889 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0741s for 16384 events => throughput is 2.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1094s for 243889 events => throughput is 2.23E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2963s for 243889 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0798s for 49152 events => throughput is 6.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0348s for 16384 events => throughput is 4.70E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0739s for 16384 events => throughput is 2.22E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1087s for 243889 events => throughput is 2.24E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8970s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7565s [COUNTERS] OVERALL MEs ( 32 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5189s - [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] PROGRAM TOTAL : 1.3325s + [COUNTERS] Fortran Other ( 0 ) : 0.0405s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6177s for 320856 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 49152 events => throughput is 6.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4314s for 320856 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0491s for 16384 events => throughput is 3.34E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0493s for 16384 events => throughput is 3.32E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 320856 events => throughput is 4.42E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9916s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8057s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G34/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2381s - [COUNTERS] Fortran Other ( 0 ) : 0.0997s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2200s for 1259120 events => throughput is 5.67E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.32E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0505s for 16384 events => throughput is 3.24E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0964s for 1259120 events => throughput is 1.31E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.5765s + [COUNTERS] Fortran Other ( 0 ) : 0.0984s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5588s for 1259120 events => throughput is 8.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0864s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0507s for 16384 events => throughput is 3.23E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0960s for 1259120 events => throughput is 1.31E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.7109s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0496s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7735s - [COUNTERS] Fortran Other ( 0 ) : 0.0514s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7232s for 403861 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5366s + [COUNTERS] Fortran Other ( 0 ) : 0.0501s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4881s for 403861 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0790s for 49152 events => throughput is 6.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1073s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1518s for 403861 events => throughput is 2.66E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1515s for 403861 events => throughput is 2.66E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2454s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5280s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0095s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 2.0064 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 1.6855 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0265s - [COUNTERS] Fortran Other ( 0 ) : 0.0417s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5514s for 285337 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0831s for 81920 events => throughput is 9.86E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0406s for 16384 events => throughput is 4.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0261s for 16384 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0413s for 285337 events => throughput is 6.91E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.8603s + [COUNTERS] Fortran Other ( 0 ) : 0.0415s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3846s for 285337 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0837s for 81920 events => throughput is 9.79E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0410s for 16384 events => throughput is 4.00E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0260s for 16384 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 285337 events => throughput is 6.93E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1632s for 16384 events => throughput is 1.00E+05 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8632s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1632s for 16384 events => throughput is 1.00E+05 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1634s for 16384 events => throughput is 1.00E+05 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6969s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1634s for 16384 events => throughput is 1.00E+05 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G46/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9608s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4729s for 258650 events => throughput is 5.47E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0422s for 16384 events => throughput is 3.89E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8062s + [COUNTERS] Fortran Other ( 0 ) : 0.0416s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3184s for 258650 events => throughput is 8.12E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0422s for 16384 events => throughput is 3.88E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0378s for 16384 events => throughput is 4.33E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0538s for 258650 events => throughput is 4.81E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0037s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 258650 events => throughput is 4.81E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1640s for 16384 events => throughput is 9.99E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7968s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6422s [COUNTERS] OVERALL MEs ( 32 ) : 0.1640s for 16384 events => throughput is 9.99E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 2.4165 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 1.9319 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G25/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5696s - [COUNTERS] Fortran Other ( 0 ) : 0.0687s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0989s for 669977 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2049s + [COUNTERS] Fortran Other ( 0 ) : 0.0677s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7360s for 669977 events => throughput is 9.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0631s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 4.98E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0221s for 669977 events => throughput is 3.03E+07 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0031s for 16384 events => throughput is 5.23E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0216s for 669977 events => throughput is 3.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1656s for 16384 events => throughput is 9.90E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4040s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1656s for 16384 events => throughput is 9.90E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1658s for 16384 events => throughput is 9.88E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0392s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1658s for 16384 events => throughput is 9.88E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8275s - [COUNTERS] Fortran Other ( 0 ) : 0.0346s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3703s for 205420 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0685s for 16384 events => throughput is 2.39E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7082s + [COUNTERS] Fortran Other ( 0 ) : 0.0343s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2511s for 205420 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0690s for 16384 events => throughput is 2.37E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0151s for 16384 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0260s for 205420 events => throughput is 7.89E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.97E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6623s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1649s for 16384 events => throughput is 9.94E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5433s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1649s for 16384 events => throughput is 9.94E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 9.4599 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 8.4848 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3791s - [COUNTERS] Fortran Other ( 0 ) : 0.0359s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3910s for 218285 events => throughput is 5.58E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2500s + [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2643s for 218285 events => throughput is 8.26E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0772s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0722s for 16384 events => throughput is 2.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1172s for 218285 events => throughput is 1.86E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0721s for 16384 events => throughput is 2.27E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1165s for 218285 events => throughput is 1.87E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5278s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8513s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5278s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7229s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4445s - [COUNTERS] Fortran Other ( 0 ) : 0.0453s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5728s for 318651 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0361s for 16384 events => throughput is 4.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 318651 events => throughput is 5.93E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 1.2532s + [COUNTERS] Fortran Other ( 0 ) : 0.0443s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3835s for 318651 events => throughput is 8.31E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0535s for 318651 events => throughput is 5.96E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9175s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5266s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7266s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5266s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2252s - [COUNTERS] Fortran Other ( 0 ) : 0.0333s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3030s for 164085 events => throughput is 5.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1252s + [COUNTERS] Fortran Other ( 0 ) : 0.0329s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2027s for 164085 events => throughput is 8.09E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0514s for 16384 events => throughput is 3.19E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0515s for 16384 events => throughput is 3.18E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0725s for 164085 events => throughput is 2.26E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6955s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5294s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5958s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5294s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2138s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3422s for 177884 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0772s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 4.00E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0572s for 177884 events => throughput is 3.11E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.1104s + [COUNTERS] Fortran Other ( 0 ) : 0.0334s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2394s for 177884 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 3.99E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0573s for 177884 events => throughput is 3.11E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6864s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5829s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5275s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1707s - [COUNTERS] Fortran Other ( 0 ) : 0.0354s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3759s for 206659 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0488s + [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2541s for 206659 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0095s for 16384 events => throughput is 1.72E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.09E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.10E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6437s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5270s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5221s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5267s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2195s + [COUNTERS] PROGRAM TOTAL : 1.1066s [COUNTERS] Fortran Other ( 0 ) : 0.0363s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3346s for 195643 events => throughput is 5.85E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0806s for 16384 events => throughput is 2.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0326s for 16384 events => throughput is 5.02E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 195643 events => throughput is 3.26E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2220s for 195643 events => throughput is 8.81E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0324s for 16384 events => throughput is 5.05E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0601s for 195643 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5266s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6930s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5266s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5798s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5268s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7452s - [COUNTERS] Fortran Other ( 0 ) : 0.0480s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6645s for 370750 events => throughput is 5.58E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5299s + [COUNTERS] Fortran Other ( 0 ) : 0.0473s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4495s for 370750 events => throughput is 8.25E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1140s for 16384 events => throughput is 1.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1771s for 370750 events => throughput is 2.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1141s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1774s for 370750 events => throughput is 2.09E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5301s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2151s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5301s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0002s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5297s for 16384 events => throughput is 3.09E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.1534 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 1.6265 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/G42/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1414s - [COUNTERS] Fortran Other ( 0 ) : 0.0891s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5095s for 974583 events => throughput is 6.46E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6150s + [COUNTERS] Fortran Other ( 0 ) : 0.0890s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9839s for 974583 events => throughput is 9.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0583s for 16384 events => throughput is 2.81E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0942s for 974583 events => throughput is 1.03E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0941s for 974583 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1645s for 16384 events => throughput is 9.96E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9768s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1645s for 16384 events => throughput is 9.96E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1643s for 16384 events => throughput is 9.97E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4507s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1643s for 16384 events => throughput is 9.97E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 27.9482 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 23.2719 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4034s - [COUNTERS] Fortran Other ( 0 ) : 0.0771s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4266s for 850849 events => throughput is 5.96E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9636s + [COUNTERS] Fortran Other ( 0 ) : 0.0774s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9870s for 850849 events => throughput is 8.62E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1096s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0370s for 16384 events => throughput is 4.43E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1086s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0371s for 16384 events => throughput is 4.42E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 850849 events => throughput is 1.27E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5303s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8732s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5303s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5305s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4331s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5305s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3174s - [COUNTERS] Fortran Other ( 0 ) : 0.0728s + [COUNTERS] PROGRAM TOTAL : 1.8940s + [COUNTERS] Fortran Other ( 0 ) : 0.0723s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3860s for 778343 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0886s for 16384 events => throughput is 1.85E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0286s for 16384 events => throughput is 5.72E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0547s for 778343 events => throughput is 1.42E+07 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9654s for 778343 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0754s for 81920 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0885s for 16384 events => throughput is 1.85E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0287s for 16384 events => throughput is 5.72E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0545s for 778343 events => throughput is 1.43E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5302s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7872s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5302s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3647s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.8786s - [COUNTERS] Fortran Other ( 0 ) : 0.1007s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9530s for 1190413 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0863s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0107s for 16384 events => throughput is 1.53E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0442s for 1190413 events => throughput is 2.69E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.2316s + [COUNTERS] Fortran Other ( 0 ) : 0.0999s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3083s for 1190413 events => throughput is 9.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0860s for 16384 events => throughput is 1.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0108s for 16384 events => throughput is 1.52E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0442s for 1190413 events => throughput is 2.70E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3514s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5272s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7047s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5269s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4521s - [COUNTERS] Fortran Other ( 0 ) : 0.0453s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5652s for 314106 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0542s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2663s + [COUNTERS] Fortran Other ( 0 ) : 0.0450s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3796s for 314106 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0402s for 16384 events => throughput is 4.07E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0618s for 314106 events => throughput is 5.08E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9225s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5296s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5288s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7375s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5288s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5376s - [COUNTERS] Fortran Other ( 0 ) : 0.0821s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4553s for 882930 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1086s for 16384 events => throughput is 1.51E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1278s for 882930 events => throughput is 6.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5294s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0082s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5294s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] PROGRAM TOTAL : 2.0625s + [COUNTERS] Fortran Other ( 0 ) : 0.0809s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9803s for 882930 events => throughput is 9.01E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1089s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1282s for 882930 events => throughput is 6.89E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5300s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5325s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5300s for 16384 events => throughput is 3.09E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2944s - [COUNTERS] Fortran Other ( 0 ) : 0.0341s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3380s for 187611 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0819s for 16384 events => throughput is 2.00E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1827s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2286s for 187611 events => throughput is 8.21E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0609s for 16384 events => throughput is 2.69E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0948s for 187611 events => throughput is 1.98E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0608s for 16384 events => throughput is 2.69E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0947s for 187611 events => throughput is 1.98E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5290s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7654s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5290s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6543s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5284s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.9253s - [COUNTERS] Fortran Other ( 0 ) : 0.1366s + [COUNTERS] PROGRAM TOTAL : 2.9975s + [COUNTERS] Fortran Other ( 0 ) : 0.1352s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.7984s for 1696178 events => throughput is 6.06E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8716s for 1696178 events => throughput is 9.06E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0873s for 16384 events => throughput is 1.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0876s for 16384 events => throughput is 1.87E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0828s for 16384 events => throughput is 1.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1435s for 1696178 events => throughput is 1.18E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1434s for 1696178 events => throughput is 1.18E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5290s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 3.3962s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5290s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4682s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1695s - [COUNTERS] Fortran Other ( 0 ) : 0.0314s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2686s for 138227 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0749s for 138227 events => throughput is 1.84E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0874s + [COUNTERS] Fortran Other ( 0 ) : 0.0315s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1872s for 138227 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0540s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0751s for 138227 events => throughput is 1.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5295s for 16384 events => throughput is 3.09E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6400s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5295s for 16384 events => throughput is 3.09E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5286s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5588s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5286s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2687s - [COUNTERS] Fortran Other ( 0 ) : 0.0396s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3687s for 215899 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0303s for 16384 events => throughput is 5.41E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1393s + [COUNTERS] Fortran Other ( 0 ) : 0.0395s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2401s for 215899 events => throughput is 8.99E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0301s for 16384 events => throughput is 5.44E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0664s for 215899 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7413s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5273s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5276s for 16384 events => throughput is 3.11E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6117s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5276s for 16384 events => throughput is 3.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3259s - [COUNTERS] Fortran Other ( 0 ) : 0.0395s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4915s for 254421 events => throughput is 5.18E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.1731s + [COUNTERS] Fortran Other ( 0 ) : 0.0387s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3409s for 254421 events => throughput is 7.46E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0209s for 16384 events => throughput is 7.85E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0341s for 254421 events => throughput is 7.46E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0542s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.87E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0341s for 254421 events => throughput is 7.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.5292s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7967s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6439s [COUNTERS] OVERALL MEs ( 32 ) : 0.5292s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9427s - [COUNTERS] Fortran Other ( 0 ) : 0.0928s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8660s for 1024423 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0864s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1333s for 1024423 events => throughput is 7.69E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.3278s + [COUNTERS] Fortran Other ( 0 ) : 0.0866s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2579s for 1024423 events => throughput is 8.14E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1327s for 1024423 events => throughput is 7.72E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5291s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4136s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5291s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7985s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5293s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2350s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s + [COUNTERS] PROGRAM TOTAL : 1.1203s + [COUNTERS] Fortran Other ( 0 ) : 0.0367s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3332s for 193396 events => throughput is 5.80E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0964s for 16384 events => throughput is 1.70E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0316s for 16384 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 193396 events => throughput is 3.22E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2199s for 193396 events => throughput is 8.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0945s for 16384 events => throughput is 1.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.17E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0604s for 193396 events => throughput is 3.20E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5292s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7059s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5292s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5294s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5909s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5294s for 16384 events => throughput is 3.10E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6785s - [COUNTERS] Fortran Other ( 0 ) : 0.0489s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6516s for 362054 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0959s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1452s for 362054 events => throughput is 2.49E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s + [COUNTERS] PROGRAM TOTAL : 1.4638s + [COUNTERS] Fortran Other ( 0 ) : 0.0485s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4379s for 362054 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0962s for 16384 events => throughput is 1.70E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1454s for 362054 events => throughput is 2.49E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5256s for 16384 events => throughput is 3.12E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1528s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5256s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5250s for 16384 events => throughput is 3.12E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9388s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5250s for 16384 events => throughput is 3.12E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G76/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4010s - [COUNTERS] Fortran Other ( 0 ) : 0.0455s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4552s for 265638 events => throughput is 5.84E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0768s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0501s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0887s for 265638 events => throughput is 3.00E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s + [COUNTERS] PROGRAM TOTAL : 1.2441s + [COUNTERS] Fortran Other ( 0 ) : 0.0451s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2986s for 265638 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0770s for 16384 events => throughput is 2.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0502s for 16384 events => throughput is 3.26E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0888s for 265638 events => throughput is 2.99E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.5291s for 16384 events => throughput is 3.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8719s - [COUNTERS] OVERALL MEs ( 32 ) : 0.5291s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.5288s for 16384 events => throughput is 3.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7153s + [COUNTERS] OVERALL MEs ( 32 ) : 0.5288s for 16384 events => throughput is 3.10E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.1569 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.0019 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1457s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4907s for 259134 events => throughput is 5.28E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0318s for 16384 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0479s for 259134 events => throughput is 5.41E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9905s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3357s for 259134 events => throughput is 7.72E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0352s for 16384 events => throughput is 4.65E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.16E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 259134 events => throughput is 5.43E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3435s for 16384 events => throughput is 4.77E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8022s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3435s for 16384 events => throughput is 4.77E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3432s for 16384 events => throughput is 4.77E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6473s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3432s for 16384 events => throughput is 4.77E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 3.2181 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 2.7778 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7819s - [COUNTERS] Fortran Other ( 0 ) : 0.0349s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3381s for 187490 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0678s for 16384 events => throughput is 2.42E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.10E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0167s for 187490 events => throughput is 1.12E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] PROGRAM TOTAL : 0.6724s + [COUNTERS] Fortran Other ( 0 ) : 0.0347s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2287s for 187490 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0676s for 16384 events => throughput is 2.42E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.09E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0166s for 187490 events => throughput is 1.13E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1665s for 16384 events => throughput is 9.84E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6154s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1665s for 16384 events => throughput is 9.84E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1673s for 16384 events => throughput is 9.79E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5051s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1673s for 16384 events => throughput is 9.79E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8630s - [COUNTERS] Fortran Other ( 0 ) : 0.0402s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4136s for 229909 events => throughput is 5.56E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7278s + [COUNTERS] Fortran Other ( 0 ) : 0.0396s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2775s for 229909 events => throughput is 8.29E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0437s for 16384 events => throughput is 3.75E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0179s for 16384 events => throughput is 9.15E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0303s for 229909 events => throughput is 7.59E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0439s for 16384 events => throughput is 3.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0179s for 16384 events => throughput is 9.13E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0302s for 229909 events => throughput is 7.60E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1684s for 16384 events => throughput is 9.73E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6946s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1684s for 16384 events => throughput is 9.73E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1690s for 16384 events => throughput is 9.69E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5588s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1690s for 16384 events => throughput is 9.69E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7787s - [COUNTERS] Fortran Other ( 0 ) : 0.0342s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3240s for 170163 events => throughput is 5.25E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0457s for 16384 events => throughput is 3.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0237s for 16384 events => throughput is 6.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0354s for 170163 events => throughput is 4.81E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0004s + [COUNTERS] PROGRAM TOTAL : 0.6804s + [COUNTERS] Fortran Other ( 0 ) : 0.0332s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2254s for 170163 events => throughput is 7.55E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0456s for 16384 events => throughput is 3.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0239s for 16384 events => throughput is 6.86E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0357s for 170163 events => throughput is 4.76E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1664s for 16384 events => throughput is 9.85E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6124s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5140s [COUNTERS] OVERALL MEs ( 32 ) : 0.1664s for 16384 events => throughput is 9.85E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7597s - [COUNTERS] Fortran Other ( 0 ) : 0.0322s + [COUNTERS] PROGRAM TOTAL : 0.6625s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2839s for 155440 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0695s for 16384 events => throughput is 2.36E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0206s for 16384 events => throughput is 7.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0311s for 155440 events => throughput is 5.00E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1928s for 155440 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0696s for 16384 events => throughput is 2.35E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 7.99E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0311s for 155440 events => throughput is 5.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1727s for 16384 events => throughput is 9.49E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5870s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1727s for 16384 events => throughput is 9.49E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1666s for 16384 events => throughput is 9.83E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4959s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1666s for 16384 events => throughput is 9.83E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 5.9306 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 5.3988 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3954s - [COUNTERS] Fortran Other ( 0 ) : 0.0374s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3642s for 193303 events => throughput is 5.31E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2799s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0430s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2475s for 193303 events => throughput is 7.81E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0802s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0541s for 16384 events => throughput is 3.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0046s for 16384 events => throughput is 3.57E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 193303 events => throughput is 1.48E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0047s for 16384 events => throughput is 3.51E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0127s for 193303 events => throughput is 1.52E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7623s for 16384 events => throughput is 2.15E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6331s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7623s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7632s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5167s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7632s for 16384 events => throughput is 2.15E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G21/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8085s - [COUNTERS] Fortran Other ( 0 ) : 0.0535s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6784s for 430212 events => throughput is 6.34E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5713s + [COUNTERS] Fortran Other ( 0 ) : 0.0532s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4438s for 430212 events => throughput is 9.69E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1044s for 16384 events => throughput is 1.57E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.45E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0333s for 430212 events => throughput is 1.29E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1029s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.48E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0332s for 430212 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7618s for 16384 events => throughput is 2.15E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0467s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7618s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7615s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8098s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7615s for 16384 events => throughput is 2.15E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3495s - [COUNTERS] Fortran Other ( 0 ) : 0.0320s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2870s for 154293 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0817s for 49152 events => throughput is 6.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0351s for 16384 events => throughput is 4.67E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0100s for 16384 events => throughput is 1.64E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.57E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.2597s + [COUNTERS] Fortran Other ( 0 ) : 0.0318s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1980s for 154293 events => throughput is 7.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0810s for 49152 events => throughput is 6.07E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0101s for 16384 events => throughput is 1.62E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0181s for 154293 events => throughput is 8.51E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7624s for 16384 events => throughput is 2.15E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5871s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7624s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7617s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4980s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7617s for 16384 events => throughput is 2.15E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3407s - [COUNTERS] Fortran Other ( 0 ) : 0.0316s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3179s for 159370 events => throughput is 5.01E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2516s + [COUNTERS] Fortran Other ( 0 ) : 0.0319s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2264s for 159370 events => throughput is 7.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0528s for 16384 events => throughput is 3.11E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.05E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.04E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0129s for 159370 events => throughput is 1.23E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7613s for 16384 events => throughput is 2.15E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5794s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7613s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7630s for 16384 events => throughput is 2.15E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4885s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7630s for 16384 events => throughput is 2.15E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.6269 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.2236 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8575s - [COUNTERS] Fortran Other ( 0 ) : 0.0368s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3844s for 212440 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0706s for 49152 events => throughput is 6.96E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0682s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0202s for 16384 events => throughput is 8.11E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 212440 events => throughput is 6.59E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7318s + [COUNTERS] Fortran Other ( 0 ) : 0.0360s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2598s for 212440 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0203s for 16384 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1651s for 16384 events => throughput is 9.93E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6924s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1651s for 16384 events => throughput is 9.93E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5666s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8906s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s + [COUNTERS] PROGRAM TOTAL : 0.7404s + [COUNTERS] Fortran Other ( 0 ) : 0.0410s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4535s for 250568 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0707s for 49152 events => throughput is 6.95E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0439s for 16384 events => throughput is 3.73E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3040s for 250568 events => throughput is 8.24E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.77E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0126s for 16384 events => throughput is 1.30E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0241s for 250568 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7254s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1652s for 16384 events => throughput is 9.92E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1653s for 16384 events => throughput is 9.91E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5751s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1653s for 16384 events => throughput is 9.91E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8522s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4112s for 227751 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0677s for 16384 events => throughput is 2.42E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.7247s + [COUNTERS] Fortran Other ( 0 ) : 0.0365s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2800s for 227751 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0680s for 16384 events => throughput is 2.41E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0061s for 16384 events => throughput is 2.68E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.46E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.47E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1649s for 16384 events => throughput is 9.94E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6873s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1649s for 16384 events => throughput is 9.94E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1687s for 16384 events => throughput is 9.71E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5560s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1687s for 16384 events => throughput is 9.71E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.8198 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.7171 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8093s - [COUNTERS] Fortran Other ( 0 ) : 0.0326s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3563s for 184243 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0446s for 16384 events => throughput is 3.67E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.57E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 184243 events => throughput is 4.86E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7049s + [COUNTERS] Fortran Other ( 0 ) : 0.0334s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0432s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2506s for 184243 events => throughput is 7.35E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0442s for 16384 events => throughput is 3.70E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.58E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 184243 events => throughput is 4.87E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1647s for 16384 events => throughput is 9.95E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6446s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1647s for 16384 events => throughput is 9.95E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1646s for 16384 events => throughput is 9.96E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5404s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1646s for 16384 events => throughput is 9.96E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 2.5962 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 1.9686 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/G14/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5854s - [COUNTERS] Fortran Other ( 0 ) : 0.0983s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8829s for 1143085 events => throughput is 6.07E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9572s + [COUNTERS] Fortran Other ( 0 ) : 0.0966s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2561s for 1143085 events => throughput is 9.10E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0686s for 49152 events => throughput is 7.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0567s for 16384 events => throughput is 2.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0109s for 16384 events => throughput is 1.51E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0433s for 1143085 events => throughput is 2.64E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0568s for 16384 events => throughput is 2.88E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0109s for 16384 events => throughput is 1.50E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0428s for 1143085 events => throughput is 2.67E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3459s for 16384 events => throughput is 4.74E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2395s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3459s for 16384 events => throughput is 4.74E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3457s for 16384 events => throughput is 4.74E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6115s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3457s for 16384 events => throughput is 4.74E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 5.7722 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 5.3094 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1299s + [COUNTERS] PROGRAM TOTAL : 1.8772s [COUNTERS] Fortran Other ( 0 ) : 0.0462s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6180s for 332018 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4236s for 332018 events => throughput is 7.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0788s for 332018 events => throughput is 4.22E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0532s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0787s for 332018 events => throughput is 4.22E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.1239s for 16384 events => throughput is 1.46E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0060s - [COUNTERS] OVERALL MEs ( 32 ) : 1.1239s for 16384 events => throughput is 1.46E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0650s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8122s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0650s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8383s - [COUNTERS] Fortran Other ( 0 ) : 0.0346s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3396s for 183011 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.7366s + [COUNTERS] Fortran Other ( 0 ) : 0.0347s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2362s for 183011 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0630s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0991s for 183011 events => throughput is 1.85E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1010s for 183011 events => throughput is 1.81E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0044s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7734s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0649s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6709s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.7767s - [COUNTERS] Fortran Other ( 0 ) : 0.0367s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3474s for 193329 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0801s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0355s for 16384 events => throughput is 4.62E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.6684s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2403s for 193329 events => throughput is 8.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0356s for 16384 events => throughput is 4.61E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0609s for 193329 events => throughput is 3.17E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0665s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7102s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0665s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6028s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0656s for 16384 events => throughput is 1.54E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.9156 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 0.7729 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9047s - [COUNTERS] Fortran Other ( 0 ) : 0.0395s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4375s for 243014 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0668s for 49152 events => throughput is 7.35E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.78E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0415s for 243014 events => throughput is 5.85E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.7619s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2952s for 243014 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0667s for 49152 events => throughput is 7.36E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0437s for 16384 events => throughput is 3.75E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.35E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 243014 events => throughput is 5.90E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.1708s for 16384 events => throughput is 9.59E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7338s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5911s [COUNTERS] OVERALL MEs ( 32 ) : 0.1708s for 16384 events => throughput is 9.59E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.8818 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 1.7200 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9422s - [COUNTERS] Fortran Other ( 0 ) : 0.0315s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2770s for 152585 events => throughput is 5.51E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0800s for 49152 events => throughput is 6.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0823s for 16384 events => throughput is 1.99E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8516s + [COUNTERS] Fortran Other ( 0 ) : 0.0314s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1869s for 152585 events => throughput is 8.17E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0803s for 49152 events => throughput is 6.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0831s for 16384 events => throughput is 1.97E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0049s for 16384 events => throughput is 3.36E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0123s for 152585 events => throughput is 1.24E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0049s for 16384 events => throughput is 3.32E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0122s for 152585 events => throughput is 1.25E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3744s for 16384 events => throughput is 4.38E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5679s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3744s for 16384 events => throughput is 4.38E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3731s for 16384 events => throughput is 4.39E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4784s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3731s for 16384 events => throughput is 4.39E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G62/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9198s - [COUNTERS] Fortran Other ( 0 ) : 0.0289s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2218s for 121146 events => throughput is 5.46E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0798s for 49152 events => throughput is 6.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0836s for 16384 events => throughput is 1.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 7.97E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 121146 events => throughput is 3.77E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0041s + [COUNTERS] PROGRAM TOTAL : 0.8488s + [COUNTERS] Fortran Other ( 0 ) : 0.0293s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1507s for 121146 events => throughput is 8.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0797s for 49152 events => throughput is 6.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0830s for 16384 events => throughput is 1.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0207s for 16384 events => throughput is 7.91E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0321s for 121146 events => throughput is 3.77E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0042s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.3733s for 16384 events => throughput is 4.39E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5465s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4756s [COUNTERS] OVERALL MEs ( 32 ) : 0.3733s for 16384 events => throughput is 4.39E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 2.1156 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 1.9302 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1049s - [COUNTERS] Fortran Other ( 0 ) : 0.0423s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6539s for 329671 events => throughput is 5.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0505s for 16384 events => throughput is 3.24E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9187s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4636s for 329671 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0509s for 16384 events => throughput is 3.22E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0556s for 16384 events => throughput is 2.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0818s for 329671 events => throughput is 4.03E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0811s for 329671 events => throughput is 4.07E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0043s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.0627s for 16384 events => throughput is 1.54E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0422s - [COUNTERS] OVERALL MEs ( 32 ) : 1.0627s for 16384 events => throughput is 1.54E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.0680s for 16384 events => throughput is 1.53E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8507s + [COUNTERS] OVERALL MEs ( 32 ) : 1.0680s for 16384 events => throughput is 1.53E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.9994 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 0.8485 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/G7/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9886s - [COUNTERS] Fortran Other ( 0 ) : 0.0410s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4934s for 255151 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.90E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0411s for 16384 events => throughput is 3.98E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8376s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3433s for 255151 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0826s for 81920 events => throughput is 9.92E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0416s for 16384 events => throughput is 3.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0510s for 255151 events => throughput is 5.00E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0004s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1659s for 16384 events => throughput is 9.88E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8227s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1659s for 16384 events => throughput is 9.88E+04 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0508s for 255151 events => throughput is 5.02E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1664s for 16384 events => throughput is 9.85E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6712s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1664s for 16384 events => throughput is 9.85E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.5577 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.3450 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.7088s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2939s for 159224 events => throughput is 5.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.6119s + [COUNTERS] Fortran Other ( 0 ) : 0.0334s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1964s for 159224 events => throughput is 8.11E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.03E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0439s for 16384 events => throughput is 3.73E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0056s for 16384 events => throughput is 2.94E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0133s for 159224 events => throughput is 1.20E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0442s for 16384 events => throughput is 3.70E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.01E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0132s for 159224 events => throughput is 1.21E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1693s for 16384 events => throughput is 9.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5395s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1693s for 16384 events => throughput is 9.68E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1698s for 16384 events => throughput is 9.65E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4420s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1698s for 16384 events => throughput is 9.65E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.8301s - [COUNTERS] Fortran Other ( 0 ) : 0.0345s + [COUNTERS] PROGRAM TOTAL : 0.7132s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3895s for 201854 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2724s for 201854 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.83E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0166s for 16384 events => throughput is 9.89E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.30E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0275s for 201854 events => throughput is 7.34E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.1693s for 16384 events => throughput is 9.68E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6608s - [COUNTERS] OVERALL MEs ( 32 ) : 0.1693s for 16384 events => throughput is 9.68E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.1703s for 16384 events => throughput is 9.62E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5429s + [COUNTERS] OVERALL MEs ( 32 ) : 0.1703s for 16384 events => throughput is 9.62E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 1.1151 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 0.9600 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1043s - [COUNTERS] Fortran Other ( 0 ) : 0.0419s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4969s for 268443 events => throughput is 5.40E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9486s + [COUNTERS] Fortran Other ( 0 ) : 0.0423s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3397s for 268443 events => throughput is 7.90E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0432s for 16384 events => throughput is 3.79E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0436s for 16384 events => throughput is 3.76E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0093s for 16384 events => throughput is 1.76E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0205s for 268443 events => throughput is 1.31E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0094s for 16384 events => throughput is 1.75E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0204s for 268443 events => throughput is 1.31E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3436s for 16384 events => throughput is 4.77E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7608s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3436s for 16384 events => throughput is 4.77E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3438s for 16384 events => throughput is 4.77E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6048s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3438s for 16384 events => throughput is 4.77E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.9279 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 0.8305 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9171s - [COUNTERS] Fortran Other ( 0 ) : 0.0331s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3150s for 168484 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.01E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0665s for 16384 events => throughput is 2.47E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 4.94E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.58E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0035s + [COUNTERS] PROGRAM TOTAL : 0.8196s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2168s for 168484 events => throughput is 7.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0668s for 16384 events => throughput is 2.45E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 5.01E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.57E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0036s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3391s for 16384 events => throughput is 4.83E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5780s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3391s for 16384 events => throughput is 4.83E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3393s for 16384 events => throughput is 4.83E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4803s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3393s for 16384 events => throughput is 4.83E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 184.7759 seconds -__CUDACPP_DEBUG: gen_ximprove.launch finished in 185.3223 seconds -__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 185.3229 seconds +__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 159.7963 seconds +__CUDACPP_DEBUG: gen_ximprove.launch finished in 160.3575 seconds +__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 160.3581 seconds __CUDACPP_DEBUG: GridPackCmd.launch (3a) combine_events combine_events __CUDACPP_DEBUG: GridPackCmd.launch (3b) store_events @@ -2116,9 +2116,9 @@ store_events INFO: No version of lhapdf. Can not run systematics computation decay_events -from_cards -__CUDACPP_DEBUG: GridPackCmd.launch finished in 187.9709 seconds +__CUDACPP_DEBUG: GridPackCmd.launch finished in 163.0136 seconds __CUDACPP_DEBUG: GridPackCmd.__init__ back from self.launch DONE write ./events.lhe.gz -END: Thu Aug 22 03:55:01 PM CEST 2024 -ELAPSED: 188 seconds +END: Thu Aug 22 05:08:25 PM CEST 2024 +ELAPSED: 163 seconds diff --git a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppnone/output.txt b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppnone/output.txt index b2221152a5..744402a047 100644 --- a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppnone/output.txt +++ b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppnone/output.txt @@ -1,91 +1,91 @@ -START: Thu Aug 22 03:39:28 PM CEST 2024 +START: Thu Aug 22 04:54:07 PM CEST 2024 On itgold91.cern.ch [CPU: Intel(R) Xeon(R) Gold 6326 CPU (nproc=32)] [GPU: none]: CUDACPP_RUNTIME_DISABLEFPE is set -CUDACPP_RUNTIME_SKIPXBINCHECKS is not set -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:39 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +CUDACPP_RUNTIME_SKIPXBINCHECKS is set +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 16:54 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.none_m_inl0_hrd0/madevent_cpp Now generating 100 events with random seed 21 and granularity 1 ************************************************************ * * @@ -211,1901 +211,1901 @@ __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event starting INFO: need to improve 108 channels __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 48.0288 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 45.8291 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2690s + [COUNTERS] PROGRAM TOTAL : 3.1689s [COUNTERS] Fortran Other ( 0 ) : 0.0336s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3220s for 176708 events => throughput is 5.49E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2188s for 176708 events => throughput is 8.08E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0463s for 16384 events => throughput is 3.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0685s for 176708 events => throughput is 2.58E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0465s for 16384 events => throughput is 3.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0683s for 176708 events => throughput is 2.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5557s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7133s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5557s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5566s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6122s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5566s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4849s - [COUNTERS] Fortran Other ( 0 ) : 0.0467s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6080s for 337001 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0217s for 16384 events => throughput is 7.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 337001 events => throughput is 8.88E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] PROGRAM TOTAL : 3.2841s + [COUNTERS] Fortran Other ( 0 ) : 0.0468s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4063s for 337001 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0216s for 16384 events => throughput is 7.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0376s for 337001 events => throughput is 8.95E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5530s for 16384 events => throughput is 6.42E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9320s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5530s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5537s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7304s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5537s for 16384 events => throughput is 6.42E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3658s - [COUNTERS] Fortran Other ( 0 ) : 0.0353s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3553s for 196960 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 81920 events => throughput is 1.04E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0776s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.2547s + [COUNTERS] Fortran Other ( 0 ) : 0.0359s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2424s for 196960 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0802s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0670s for 16384 events => throughput is 2.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1031s for 196960 events => throughput is 1.91E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1032s for 196960 events => throughput is 1.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5614s for 16384 events => throughput is 6.40E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8044s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5614s for 16384 events => throughput is 6.40E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5605s for 16384 events => throughput is 6.40E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6942s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5605s for 16384 events => throughput is 6.40E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5307s - [COUNTERS] Fortran Other ( 0 ) : 0.0424s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6257s for 324156 events => throughput is 5.18E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3548s + [COUNTERS] Fortran Other ( 0 ) : 0.0422s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4472s for 324156 events => throughput is 7.25E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0381s for 16384 events => throughput is 4.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0556s for 324156 events => throughput is 5.83E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 324156 events => throughput is 5.82E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5507s for 16384 events => throughput is 6.42E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9800s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5507s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5520s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8028s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5520s for 16384 events => throughput is 6.42E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2169s - [COUNTERS] Fortran Other ( 0 ) : 0.0361s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3037s for 176248 events => throughput is 5.80E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0575s for 176248 events => throughput is 3.06E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] PROGRAM TOTAL : 3.1153s + [COUNTERS] Fortran Other ( 0 ) : 0.0357s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1990s for 176248 events => throughput is 8.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0807s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.58E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0579s for 176248 events => throughput is 3.05E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6625s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5557s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5596s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5557s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1417s - [COUNTERS] Fortran Other ( 0 ) : 0.0312s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2492s for 128162 events => throughput is 5.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.0656s + [COUNTERS] Fortran Other ( 0 ) : 0.0306s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1744s for 128162 events => throughput is 7.35E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0360s for 16384 events => throughput is 4.55E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0500s for 128162 events => throughput is 2.56E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0360s for 16384 events => throughput is 4.56E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0500s for 128162 events => throughput is 2.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 2.5562s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5854s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5094s [COUNTERS] OVERALL MEs ( 32 ) : 2.5562s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G2/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.1656s - [COUNTERS] Fortran Other ( 0 ) : 0.0666s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2190s for 680231 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0843s for 16384 events => throughput is 1.94E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0484s for 680231 events => throughput is 1.41E+07 events/s + [COUNTERS] PROGRAM TOTAL : 3.7900s + [COUNTERS] Fortran Other ( 0 ) : 0.0665s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8459s for 680231 events => throughput is 8.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0846s for 16384 events => throughput is 1.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0490s for 680231 events => throughput is 1.39E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5578s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6078s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5578s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5542s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2358s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5542s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3278s - [COUNTERS] Fortran Other ( 0 ) : 0.0408s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3883s for 227876 events => throughput is 5.87E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0761s for 16384 events => throughput is 2.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0334s for 16384 events => throughput is 4.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0728s for 227876 events => throughput is 3.13E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.1941s + [COUNTERS] Fortran Other ( 0 ) : 0.0405s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2531s for 227876 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0759s for 16384 events => throughput is 2.16E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0333s for 16384 events => throughput is 4.92E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 227876 events => throughput is 3.13E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5509s for 16384 events => throughput is 6.42E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7769s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5509s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5527s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6414s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5527s for 16384 events => throughput is 6.42E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3777s - [COUNTERS] Fortran Other ( 0 ) : 0.0391s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5029s for 258529 events => throughput is 5.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0383s for 258529 events => throughput is 6.74E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.2250s + [COUNTERS] Fortran Other ( 0 ) : 0.0390s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3491s for 258529 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0519s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0242s for 16384 events => throughput is 6.76E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0383s for 258529 events => throughput is 6.75E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5567s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8210s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5567s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5568s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6681s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5568s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G75/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4881s - [COUNTERS] Fortran Other ( 0 ) : 0.0441s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5283s for 288195 events => throughput is 5.46E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3123s + [COUNTERS] Fortran Other ( 0 ) : 0.0443s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3540s for 288195 events => throughput is 8.14E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0549s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.81E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0816s for 288195 events => throughput is 3.53E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5553s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9329s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5553s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7580s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7656s - [COUNTERS] Fortran Other ( 0 ) : 0.0498s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6511s for 362045 events => throughput is 5.56E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.5497s + [COUNTERS] Fortran Other ( 0 ) : 0.0491s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4366s for 362045 events => throughput is 8.29E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0642s for 16384 events => throughput is 2.55E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1096s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1706s for 362045 events => throughput is 2.12E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0639s for 16384 events => throughput is 2.56E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1094s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1705s for 362045 events => throughput is 2.12E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5558s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2098s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5558s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9953s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5543s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2688s - [COUNTERS] Fortran Other ( 0 ) : 0.0402s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3291s for 203191 events => throughput is 6.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0775s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0367s for 16384 events => throughput is 4.47E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0670s for 203191 events => throughput is 3.03E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] PROGRAM TOTAL : 3.1469s + [COUNTERS] Fortran Other ( 0 ) : 0.0397s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2065s for 203191 events => throughput is 9.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0774s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0367s for 16384 events => throughput is 4.46E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0676s for 203191 events => throughput is 3.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5523s for 16384 events => throughput is 6.42E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7164s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5523s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5527s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5942s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5527s for 16384 events => throughput is 6.42E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2020s - [COUNTERS] Fortran Other ( 0 ) : 0.0363s + [COUNTERS] PROGRAM TOTAL : 3.0752s + [COUNTERS] Fortran Other ( 0 ) : 0.0357s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3790s for 205739 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2537s for 205739 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0056s for 16384 events => throughput is 2.91E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.41E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0057s for 16384 events => throughput is 2.88E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.42E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5548s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6472s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5548s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5546s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5206s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5546s for 16384 events => throughput is 6.41E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3046s - [COUNTERS] Fortran Other ( 0 ) : 0.0397s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3710s for 214038 events => throughput is 5.77E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0796s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1721s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2409s for 214038 events => throughput is 8.88E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0808s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0675s for 214038 events => throughput is 3.17E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0671s for 214038 events => throughput is 3.19E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5562s for 16384 events => throughput is 6.41E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7484s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5562s for 16384 events => throughput is 6.41E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5530s for 16384 events => throughput is 6.42E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6191s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5530s for 16384 events => throughput is 6.42E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 10.7802 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 10.2859 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7177s - [COUNTERS] Fortran Other ( 0 ) : 0.0497s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6239s for 344023 events => throughput is 5.51E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0832s for 81920 events => throughput is 9.85E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0568s for 16384 events => throughput is 2.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1010s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1456s for 344023 events => throughput is 2.36E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.5112s + [COUNTERS] Fortran Other ( 0 ) : 0.0499s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4155s for 344023 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0834s for 81920 events => throughput is 9.82E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0579s for 16384 events => throughput is 2.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1008s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1455s for 344023 events => throughput is 2.36E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5695s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1482s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5695s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5709s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9402s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5709s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G43/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4749s - [COUNTERS] Fortran Other ( 0 ) : 0.0389s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4098s for 214181 events => throughput is 5.23E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1355s for 212992 events => throughput is 1.57E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.3504s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2872s for 214181 events => throughput is 7.46E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1353s for 212992 events => throughput is 1.57E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0581s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0719s for 16384 events => throughput is 2.28E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1024s for 214181 events => throughput is 2.09E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0721s for 16384 events => throughput is 2.27E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 214181 events => throughput is 2.16E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 2.5710s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9038s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7794s [COUNTERS] OVERALL MEs ( 32 ) : 2.5710s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5599s - [COUNTERS] Fortran Other ( 0 ) : 0.0423s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5416s for 279555 events => throughput is 5.16E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3956s + [COUNTERS] Fortran Other ( 0 ) : 0.0420s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3772s for 279555 events => throughput is 7.41E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.1131s for 147456 events => throughput is 1.30E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0570s for 16384 events => throughput is 2.87E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0618s for 16384 events => throughput is 2.65E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0861s for 279555 events => throughput is 3.25E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0620s for 16384 events => throughput is 2.64E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0862s for 279555 events => throughput is 3.24E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5709s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9890s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5709s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5710s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8246s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5710s for 16384 events => throughput is 6.37E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 3.6359 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 3.1814 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/G67/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6245s - [COUNTERS] Fortran Other ( 0 ) : 0.0759s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2924s for 814370 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0793s for 49152 events => throughput is 6.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1102s for 16384 events => throughput is 1.49E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1693s + [COUNTERS] Fortran Other ( 0 ) : 0.0752s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8374s for 814370 events => throughput is 9.72E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0792s for 49152 events => throughput is 6.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1107s for 16384 events => throughput is 1.48E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0303s for 16384 events => throughput is 5.40E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0594s for 814370 events => throughput is 1.37E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0305s for 16384 events => throughput is 5.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0592s for 814370 events => throughput is 1.38E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0114s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8895s for 16384 events => throughput is 8.67E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7350s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8895s for 16384 events => throughput is 8.67E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8903s for 16384 events => throughput is 8.67E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2790s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8903s for 16384 events => throughput is 8.67E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 31.7593 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 30.4809 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.3459s - [COUNTERS] Fortran Other ( 0 ) : 0.0816s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.6405s for 933480 events => throughput is 5.69E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.33E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1023s for 16384 events => throughput is 1.60E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1002s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1612s for 933480 events => throughput is 5.79E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0945s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2515s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0945s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] PROGRAM TOTAL : 6.7514s + [COUNTERS] Fortran Other ( 0 ) : 0.0812s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0453s for 933480 events => throughput is 8.93E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 49152 events => throughput is 6.35E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1020s for 16384 events => throughput is 1.61E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1003s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1594s for 933480 events => throughput is 5.86E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0986s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6528s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0986s for 16384 events => throughput is 3.21E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.0074s - [COUNTERS] Fortran Other ( 0 ) : 0.0363s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4232s for 226350 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 49152 events => throughput is 6.31E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0771s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1223s for 226350 events => throughput is 1.85E+06 events/s + [COUNTERS] PROGRAM TOTAL : 5.8734s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0426s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2906s for 226350 events => throughput is 7.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.32E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0766s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1217s for 226350 events => throughput is 1.86E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1035s for 16384 events => throughput is 3.21E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9039s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1035s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1024s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7710s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1024s for 16384 events => throughput is 3.21E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.1654s - [COUNTERS] Fortran Other ( 0 ) : 0.0416s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6519s for 323984 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0506s for 16384 events => throughput is 3.24E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0635s for 16384 events => throughput is 2.58E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0930s for 323984 events => throughput is 3.48E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] PROGRAM TOTAL : 5.9794s + [COUNTERS] Fortran Other ( 0 ) : 0.0415s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4634s for 323984 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.32E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0499s for 16384 events => throughput is 3.28E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0633s for 16384 events => throughput is 2.59E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0955s for 323984 events => throughput is 3.39E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0997s for 16384 events => throughput is 3.21E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0657s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0997s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1006s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8788s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1006s for 16384 events => throughput is 3.21E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.2316s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7138s for 355559 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0511s for 16384 events => throughput is 3.21E+05 events/s + [COUNTERS] PROGRAM TOTAL : 6.0168s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5021s for 355559 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0510s for 16384 events => throughput is 3.21E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0622s for 16384 events => throughput is 2.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0930s for 355559 events => throughput is 3.83E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0621s for 16384 events => throughput is 2.64E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0929s for 355559 events => throughput is 3.83E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1043s for 16384 events => throughput is 3.21E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1273s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1043s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1013s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9156s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1013s for 16384 events => throughput is 3.21E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G92/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.9657s - [COUNTERS] Fortran Other ( 0 ) : 0.0410s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4564s for 255849 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] PROGRAM TOTAL : 5.8138s + [COUNTERS] Fortran Other ( 0 ) : 0.0409s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3041s for 255849 events => throughput is 8.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.31E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0777s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0386s for 16384 events => throughput is 4.24E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0839s for 255849 events => throughput is 3.05E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0387s for 16384 events => throughput is 4.23E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0837s for 255849 events => throughput is 3.06E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1027s for 16384 events => throughput is 3.21E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8630s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1027s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1034s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7104s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1034s for 16384 events => throughput is 3.21E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 27.3535 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 25.6849 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.0020s - [COUNTERS] Fortran Other ( 0 ) : 0.0778s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4050s for 859290 events => throughput is 6.12E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0753s for 81920 events => throughput is 1.09E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1076s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0580s for 16384 events => throughput is 2.83E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0986s for 859290 events => throughput is 8.72E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] PROGRAM TOTAL : 6.5531s + [COUNTERS] Fortran Other ( 0 ) : 0.0771s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9612s for 859290 events => throughput is 8.94E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1075s for 16384 events => throughput is 1.52E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0575s for 16384 events => throughput is 2.85E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0982s for 859290 events => throughput is 8.75E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0924s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9096s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0924s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0880s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4651s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0880s for 16384 events => throughput is 3.22E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.2786s - [COUNTERS] Fortran Other ( 0 ) : 0.0926s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.7933s for 1098402 events => throughput is 6.13E+05 events/s + [COUNTERS] PROGRAM TOTAL : 6.6946s + [COUNTERS] Fortran Other ( 0 ) : 0.0920s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2103s for 1098402 events => throughput is 9.08E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0790s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0124s for 16384 events => throughput is 1.32E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0125s for 16384 events => throughput is 1.31E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.55E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0955s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1831s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0955s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0942s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6004s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0942s for 16384 events => throughput is 3.22E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.2281s - [COUNTERS] Fortran Other ( 0 ) : 0.0448s + [COUNTERS] PROGRAM TOTAL : 6.0094s + [COUNTERS] Fortran Other ( 0 ) : 0.0445s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7459s for 378380 events => throughput is 5.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5281s for 378380 events => throughput is 7.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0767s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0851s for 378380 events => throughput is 4.45E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0847s for 378380 events => throughput is 4.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0791s for 16384 events => throughput is 3.23E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1490s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0791s for 16384 events => throughput is 3.23E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0772s for 16384 events => throughput is 3.23E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9322s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0772s for 16384 events => throughput is 3.23E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G65/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.8095s - [COUNTERS] Fortran Other ( 0 ) : 0.0731s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3507s for 819579 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0810s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0146s for 16384 events => throughput is 1.12E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0391s for 819579 events => throughput is 2.10E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0960s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7135s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0960s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] PROGRAM TOTAL : 6.3921s + [COUNTERS] Fortran Other ( 0 ) : 0.0729s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9343s for 819579 events => throughput is 8.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0144s for 16384 events => throughput is 1.14E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0390s for 819579 events => throughput is 2.10E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0946s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2976s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0946s for 16384 events => throughput is 3.22E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 3.5331 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 3.3396 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5210s - [COUNTERS] Fortran Other ( 0 ) : 0.0437s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6367s for 330261 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0872s for 81920 events => throughput is 9.39E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0557s for 16384 events => throughput is 2.94E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3284s + [COUNTERS] Fortran Other ( 0 ) : 0.0433s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4443s for 330261 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0871s for 81920 events => throughput is 9.41E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0559s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0073s for 16384 events => throughput is 2.25E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0199s for 330261 events => throughput is 1.66E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0196s for 330261 events => throughput is 1.68E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5832s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9378s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5832s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5838s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7446s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5838s for 16384 events => throughput is 6.34E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 3.6035 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 3.0976 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5924s - [COUNTERS] Fortran Other ( 0 ) : 0.0835s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4458s for 919173 events => throughput is 6.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0841s for 16384 events => throughput is 1.95E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1315s for 919173 events => throughput is 6.99E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.0865s + [COUNTERS] Fortran Other ( 0 ) : 0.0829s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9420s for 919173 events => throughput is 9.76E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0836s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1312s for 919173 events => throughput is 7.01E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 1.6159s for 16384 events => throughput is 1.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9765s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4706s [COUNTERS] OVERALL MEs ( 32 ) : 1.6159s for 16384 events => throughput is 1.01E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 26.0881 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 23.6575 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2582s - [COUNTERS] Fortran Other ( 0 ) : 0.0317s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2786s for 142763 events => throughput is 5.13E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0563s for 16384 events => throughput is 2.91E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0653s for 16384 events => throughput is 2.51E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0902s for 142763 events => throughput is 1.58E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.1724s + [COUNTERS] Fortran Other ( 0 ) : 0.0320s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1936s for 142763 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0564s for 16384 events => throughput is 2.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0648s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0899s for 142763 events => throughput is 1.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5725s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6857s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5725s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5721s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6003s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5721s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.0673s - [COUNTERS] Fortran Other ( 0 ) : 0.0970s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8433s for 1119813 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1099s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1084s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.4634s + [COUNTERS] Fortran Other ( 0 ) : 0.0959s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2432s for 1119813 events => throughput is 9.01E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1095s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1081s for 16384 events => throughput is 1.52E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1707s for 1119813 events => throughput is 6.56E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5748s for 16384 events => throughput is 6.36E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4925s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5748s for 16384 events => throughput is 6.36E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5723s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8911s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5723s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.2260s - [COUNTERS] Fortran Other ( 0 ) : 0.1093s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2299s for 1357398 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0866s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0172s for 16384 events => throughput is 9.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 1357398 events => throughput is 2.44E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] PROGRAM TOTAL : 4.4787s + [COUNTERS] Fortran Other ( 0 ) : 0.1086s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4826s for 1357398 events => throughput is 9.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0873s for 16384 events => throughput is 1.88E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0172s for 16384 events => throughput is 9.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0554s for 1357398 events => throughput is 2.45E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5635s for 16384 events => throughput is 6.39E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6624s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5635s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5632s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9155s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5632s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8411s - [COUNTERS] Fortran Other ( 0 ) : 0.0520s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7207s for 398526 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0560s for 16384 events => throughput is 2.92E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1145s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1688s for 398526 events => throughput is 2.36E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.6015s + [COUNTERS] Fortran Other ( 0 ) : 0.0513s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4869s for 398526 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1142s for 16384 events => throughput is 1.43E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1648s for 398526 events => throughput is 2.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5736s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2675s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5736s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5739s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0276s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5739s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G53/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.1818s - [COUNTERS] Fortran Other ( 0 ) : 0.0909s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9625s for 1103762 events => throughput is 5.62E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.5892s + [COUNTERS] Fortran Other ( 0 ) : 0.0900s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3711s for 1103762 events => throughput is 8.05E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0861s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1208s for 16384 events => throughput is 1.36E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1834s for 1103762 events => throughput is 6.02E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0857s for 16384 events => throughput is 1.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1215s for 16384 events => throughput is 1.35E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1833s for 1103762 events => throughput is 6.02E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5744s for 16384 events => throughput is 6.36E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6074s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5744s for 16384 events => throughput is 6.36E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5735s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0157s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5735s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4603s - [COUNTERS] Fortran Other ( 0 ) : 0.0440s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4667s for 272273 events => throughput is 5.83E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.2995s + [COUNTERS] Fortran Other ( 0 ) : 0.0442s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3065s for 272273 events => throughput is 8.88E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0583s for 16384 events => throughput is 2.81E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1096s for 272273 events => throughput is 2.49E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0587s for 16384 events => throughput is 2.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0528s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1096s for 272273 events => throughput is 2.48E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5736s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8867s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5736s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5718s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7277s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5718s for 16384 events => throughput is 6.37E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 4.3272 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 4.2665 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/G71/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.3165s - [COUNTERS] Fortran Other ( 0 ) : 0.0286s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2208s for 109714 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0820s for 49152 events => throughput is 6.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0175s for 16384 events => throughput is 9.35E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0251s for 109714 events => throughput is 4.37E+06 events/s + [COUNTERS] PROGRAM TOTAL : 4.2554s + [COUNTERS] Fortran Other ( 0 ) : 0.0302s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1564s for 109714 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0823s for 49152 events => throughput is 5.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0558s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0177s for 16384 events => throughput is 9.28E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0256s for 109714 events => throughput is 4.28E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 3.8007s for 16384 events => throughput is 4.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5158s - [COUNTERS] OVERALL MEs ( 32 ) : 3.8007s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s + [COUNTERS] CudaCpp MEs ( 19 ) : 3.8008s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4546s + [COUNTERS] OVERALL MEs ( 32 ) : 3.8008s for 16384 events => throughput is 4.31E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.8045 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.3177 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7936s - [COUNTERS] Fortran Other ( 0 ) : 0.0879s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4805s for 949349 events => throughput is 6.41E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 949349 events => throughput is 8.73E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.3067s + [COUNTERS] Fortran Other ( 0 ) : 0.0862s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9947s for 949349 events => throughput is 9.54E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0649s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1084s for 949349 events => throughput is 8.76E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8110s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9827s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8110s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8106s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4961s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8106s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 18.3757 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 17.8521 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.8916s + [COUNTERS] PROGRAM TOTAL : 5.7877s [COUNTERS] Fortran Other ( 0 ) : 0.0354s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3386s for 181152 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2336s for 181152 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0808s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0590s for 16384 events => throughput is 2.78E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0903s for 181152 events => throughput is 2.01E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1243s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7673s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1243s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1231s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6647s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1231s for 16384 events => throughput is 3.20E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.1313s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s + [COUNTERS] PROGRAM TOTAL : 5.9516s + [COUNTERS] Fortran Other ( 0 ) : 0.0417s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5895s for 293756 events => throughput is 4.98E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4144s for 293756 events => throughput is 7.09E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0517s for 16384 events => throughput is 3.17E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0658s for 16384 events => throughput is 2.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0921s for 293756 events => throughput is 3.19E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0522s for 16384 events => throughput is 3.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0659s for 16384 events => throughput is 2.48E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0922s for 293756 events => throughput is 3.19E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1255s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0058s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1255s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1200s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8316s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1200s for 16384 events => throughput is 3.20E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.3256s - [COUNTERS] Fortran Other ( 0 ) : 0.0525s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7576s for 405834 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0698s for 49152 events => throughput is 7.04E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0536s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 6.0837s + [COUNTERS] Fortran Other ( 0 ) : 0.0520s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5178s for 405834 events => throughput is 7.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0745s for 16384 events => throughput is 2.20E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1089s for 405834 events => throughput is 3.73E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0750s for 16384 events => throughput is 2.18E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1087s for 405834 events => throughput is 3.73E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1213s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2043s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1213s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1210s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9627s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1210s for 16384 events => throughput is 3.20E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 51.3330 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 49.1716 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.0786s - [COUNTERS] Fortran Other ( 0 ) : 0.0770s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4068s for 847188 events => throughput is 6.02E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1035s for 16384 events => throughput is 1.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1231s for 847188 events => throughput is 6.88E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] PROGRAM TOTAL : 6.6341s + [COUNTERS] Fortran Other ( 0 ) : 0.0765s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9656s for 847188 events => throughput is 8.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1029s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1226s for 847188 events => throughput is 6.91E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1247s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9539s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1247s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1242s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5098s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1242s for 16384 events => throughput is 3.20E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.8349s - [COUNTERS] Fortran Other ( 0 ) : 0.0329s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3138s for 167274 events => throughput is 5.33E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0809s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0455s for 16384 events => throughput is 3.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0639s for 167274 events => throughput is 2.62E+06 events/s + [COUNTERS] PROGRAM TOTAL : 5.7357s + [COUNTERS] Fortran Other ( 0 ) : 0.0330s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2182s for 167274 events => throughput is 7.67E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0448s for 16384 events => throughput is 3.66E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0634s for 167274 events => throughput is 2.64E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1346s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7003s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1346s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1335s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6023s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1335s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.4431s - [COUNTERS] Fortran Other ( 0 ) : 0.0980s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8795s for 1150245 events => throughput is 6.12E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] PROGRAM TOTAL : 6.8362s + [COUNTERS] Fortran Other ( 0 ) : 0.0971s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2743s for 1150245 events => throughput is 9.03E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0255s for 16384 events => throughput is 6.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0605s for 1150245 events => throughput is 1.90E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.34E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 1150245 events => throughput is 1.92E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1385s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3047s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1385s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1375s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6987s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1375s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.1433s - [COUNTERS] Fortran Other ( 0 ) : 0.0479s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6587s for 355348 events => throughput is 5.39E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] PROGRAM TOTAL : 5.9311s + [COUNTERS] Fortran Other ( 0 ) : 0.0476s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4526s for 355348 events => throughput is 7.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0297s for 16384 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0480s for 355348 events => throughput is 7.40E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0296s for 16384 events => throughput is 5.54E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 355348 events => throughput is 7.44E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1409s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0024s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1409s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1366s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7945s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1366s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 7.1091s - [COUNTERS] Fortran Other ( 0 ) : 0.0785s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4162s for 864266 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1065s for 16384 events => throughput is 1.54E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1287s for 864266 events => throughput is 6.72E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1372s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9719s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1372s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] PROGRAM TOTAL : 6.6596s + [COUNTERS] Fortran Other ( 0 ) : 0.0783s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9664s for 864266 events => throughput is 8.94E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1067s for 16384 events => throughput is 1.54E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1312s for 864266 events => throughput is 6.59E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1346s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5250s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1346s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.0898s - [COUNTERS] Fortran Other ( 0 ) : 0.0402s + [COUNTERS] PROGRAM TOTAL : 5.9298s + [COUNTERS] Fortran Other ( 0 ) : 0.0400s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5653s for 285525 events => throughput is 5.05E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4009s for 285525 events => throughput is 7.12E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0537s for 16384 events => throughput is 3.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0588s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0818s for 285525 events => throughput is 3.49E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1256s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9642s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1256s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0587s for 16384 events => throughput is 2.79E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0805s for 285525 events => throughput is 3.55E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1308s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7990s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1308s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.8346s - [COUNTERS] Fortran Other ( 0 ) : 0.0371s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3401s for 189666 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0685s for 49152 events => throughput is 7.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0821s for 16384 events => throughput is 1.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0299s for 16384 events => throughput is 5.47E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0533s for 189666 events => throughput is 3.56E+06 events/s + [COUNTERS] PROGRAM TOTAL : 5.7231s + [COUNTERS] Fortran Other ( 0 ) : 0.0369s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2271s for 189666 events => throughput is 8.35E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0808s for 16384 events => throughput is 2.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0353s for 16384 events => throughput is 4.65E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0298s for 16384 events => throughput is 5.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0531s for 189666 events => throughput is 3.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1363s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6983s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1363s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1387s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5844s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1387s for 16384 events => throughput is 3.19E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.7308s + [COUNTERS] PROGRAM TOTAL : 5.6540s [COUNTERS] Fortran Other ( 0 ) : 0.0307s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2483s for 124553 events => throughput is 5.02E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0558s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1759s for 124553 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.88E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0592s for 124553 events => throughput is 2.11E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0588s for 124553 events => throughput is 2.12E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1320s for 16384 events => throughput is 3.19E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5988s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1320s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1288s for 16384 events => throughput is 3.19E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5251s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1288s for 16384 events => throughput is 3.19E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 7.2410 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 6.8494 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G48/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6007s - [COUNTERS] Fortran Other ( 0 ) : 0.0444s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5737s for 318589 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.4132s + [COUNTERS] Fortran Other ( 0 ) : 0.0443s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3879s for 318589 events => throughput is 8.21E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0876s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1294s for 318589 events => throughput is 2.46E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1290s for 318589 events => throughput is 2.47E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5474s for 16384 events => throughput is 6.43E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0533s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5474s for 16384 events => throughput is 6.43E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5468s for 16384 events => throughput is 6.43E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8664s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5468s for 16384 events => throughput is 6.43E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6200s + [COUNTERS] PROGRAM TOTAL : 3.4156s [COUNTERS] Fortran Other ( 0 ) : 0.0430s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6646s for 343552 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4615s for 343552 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.26E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0522s for 16384 events => throughput is 3.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0603s for 16384 events => throughput is 2.72E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0604s for 16384 events => throughput is 2.71E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0878s for 343552 events => throughput is 3.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5464s for 16384 events => throughput is 6.43E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0737s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5464s for 16384 events => throughput is 6.43E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5445s for 16384 events => throughput is 6.44E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8711s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5445s for 16384 events => throughput is 6.44E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 23.2305 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 21.6790 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4265s - [COUNTERS] Fortran Other ( 0 ) : 0.0361s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3988s for 223142 events => throughput is 5.60E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.2968s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2713s for 223142 events => throughput is 8.22E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0791s for 49152 events => throughput is 6.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0685s for 16384 events => throughput is 2.39E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1103s for 223142 events => throughput is 2.02E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0686s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1097s for 223142 events => throughput is 2.04E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5670s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8595s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5670s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5665s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7303s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5665s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5970s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s + [COUNTERS] PROGRAM TOTAL : 3.4071s + [COUNTERS] Fortran Other ( 0 ) : 0.0421s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6227s for 323723 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0789s for 49152 events => throughput is 6.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0598s for 16384 events => throughput is 2.74E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0866s for 323723 events => throughput is 3.74E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4350s for 323723 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0599s for 16384 events => throughput is 2.74E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0865s for 323723 events => throughput is 3.74E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5676s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0294s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5676s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5656s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8415s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5656s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4717s + [COUNTERS] PROGRAM TOTAL : 3.3342s [COUNTERS] Fortran Other ( 0 ) : 0.0373s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4375s for 243889 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2983s for 243889 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0803s for 16384 events => throughput is 2.04E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0738s for 16384 events => throughput is 2.22E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1091s for 243889 events => throughput is 2.24E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0740s for 16384 events => throughput is 2.21E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1121s for 243889 events => throughput is 2.18E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5683s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9034s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5683s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7678s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5648s - [COUNTERS] Fortran Other ( 0 ) : 0.0414s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6225s for 320856 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0491s for 16384 events => throughput is 3.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 320856 events => throughput is 4.41E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.3884s + [COUNTERS] Fortran Other ( 0 ) : 0.0412s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4335s for 320856 events => throughput is 7.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0840s for 49152 events => throughput is 5.85E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0536s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0493s for 16384 events => throughput is 3.32E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0730s for 320856 events => throughput is 4.39E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5607s for 16384 events => throughput is 6.40E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0041s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5607s for 16384 events => throughput is 6.40E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5663s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8221s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5663s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G34/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.2923s - [COUNTERS] Fortran Other ( 0 ) : 0.0991s + [COUNTERS] PROGRAM TOTAL : 4.6197s + [COUNTERS] Fortran Other ( 0 ) : 0.0988s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2231s for 1259120 events => throughput is 5.66E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5559s for 1259120 events => throughput is 8.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.33E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0868s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0504s for 16384 events => throughput is 3.25E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0965s for 1259120 events => throughput is 1.30E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0960s for 1259120 events => throughput is 1.31E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5697s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.7226s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5697s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0533s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8255s - [COUNTERS] Fortran Other ( 0 ) : 0.0504s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7266s for 403861 events => throughput is 5.56E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.5805s + [COUNTERS] Fortran Other ( 0 ) : 0.0499s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4862s for 403861 events => throughput is 8.31E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0531s for 16384 events => throughput is 3.09E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1073s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1549s for 403861 events => throughput is 2.61E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1071s for 16384 events => throughput is 1.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1512s for 403861 events => throughput is 2.67E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5675s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2580s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5675s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5667s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0138s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5667s for 16384 events => throughput is 6.38E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 3.2902 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 2.9704 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6679s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5517s for 285337 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0844s for 81920 events => throughput is 9.71E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.5005s + [COUNTERS] Fortran Other ( 0 ) : 0.0417s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3856s for 285337 events => throughput is 7.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0832s for 81920 events => throughput is 9.85E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0410s for 16384 events => throughput is 3.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0260s for 16384 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0413s for 285337 events => throughput is 6.91E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0259s for 16384 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0411s for 285337 events => throughput is 6.94E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7981s for 16384 events => throughput is 2.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8698s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7981s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7983s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7022s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7983s for 16384 events => throughput is 2.05E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G46/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6027s - [COUNTERS] Fortran Other ( 0 ) : 0.0412s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4743s for 258650 events => throughput is 5.45E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.4502s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3222s for 258650 events => throughput is 8.03E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0427s for 16384 events => throughput is 3.84E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0377s for 16384 events => throughput is 4.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0538s for 258650 events => throughput is 4.80E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0424s for 16384 events => throughput is 3.86E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0379s for 16384 events => throughput is 4.32E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 258650 events => throughput is 4.81E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7994s for 16384 events => throughput is 2.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8033s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7994s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7992s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6510s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7992s for 16384 events => throughput is 2.05E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 3.7103 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 3.2105 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G25/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2241s - [COUNTERS] Fortran Other ( 0 ) : 0.0682s + [COUNTERS] PROGRAM TOTAL : 1.8454s + [COUNTERS] Fortran Other ( 0 ) : 0.0679s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.1036s for 669977 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7373s for 669977 events => throughput is 9.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.15E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0633s for 16384 events => throughput is 2.59E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0030s for 16384 events => throughput is 5.46E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0221s for 669977 events => throughput is 3.03E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0081s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0217s for 669977 events => throughput is 3.09E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4125s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7996s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0458s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7996s for 16384 events => throughput is 2.05E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4670s - [COUNTERS] Fortran Other ( 0 ) : 0.0352s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3704s for 205420 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0686s for 49152 events => throughput is 7.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0684s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0150s for 16384 events => throughput is 1.09E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.95E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.3459s + [COUNTERS] Fortran Other ( 0 ) : 0.0349s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2506s for 205420 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0692s for 49152 events => throughput is 7.10E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0679s for 16384 events => throughput is 2.41E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0151s for 16384 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0257s for 205420 events => throughput is 7.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8000s for 16384 events => throughput is 2.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6670s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8000s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7989s for 16384 events => throughput is 2.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5471s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7989s for 16384 events => throughput is 2.05E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 23.7948 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 22.7989 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4257s - [COUNTERS] Fortran Other ( 0 ) : 0.0359s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3934s for 218285 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.2990s + [COUNTERS] Fortran Other ( 0 ) : 0.0362s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2667s for 218285 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0772s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0722s for 16384 events => throughput is 2.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1166s for 218285 events => throughput is 1.87E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0721s for 16384 events => throughput is 2.27E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1164s for 218285 events => throughput is 1.88E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5642s for 16384 events => throughput is 6.39E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8614s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5642s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5641s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7349s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5641s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4937s - [COUNTERS] Fortran Other ( 0 ) : 0.0449s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5724s for 318651 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3005s + [COUNTERS] Fortran Other ( 0 ) : 0.0439s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3831s for 318651 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0785s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0536s for 318651 events => throughput is 5.95E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0358s for 16384 events => throughput is 4.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0535s for 318651 events => throughput is 5.95E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5690s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9247s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5690s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5655s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7349s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5655s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2658s - [COUNTERS] Fortran Other ( 0 ) : 0.0332s + [COUNTERS] PROGRAM TOTAL : 3.1692s + [COUNTERS] Fortran Other ( 0 ) : 0.0329s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2986s for 164085 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0771s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0515s for 16384 events => throughput is 3.18E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0724s for 164085 events => throughput is 2.27E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2033s for 164085 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0766s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0517s for 16384 events => throughput is 3.17E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 164085 events => throughput is 2.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5671s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6986s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5671s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6023s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2570s - [COUNTERS] Fortran Other ( 0 ) : 0.0337s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3417s for 177884 events => throughput is 5.21E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0773s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0542s for 16384 events => throughput is 3.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0409s for 16384 events => throughput is 4.01E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0571s for 177884 events => throughput is 3.11E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] PROGRAM TOTAL : 3.1548s + [COUNTERS] Fortran Other ( 0 ) : 0.0329s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2392s for 177884 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0410s for 16384 events => throughput is 4.00E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0572s for 177884 events => throughput is 3.11E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5650s for 16384 events => throughput is 6.39E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6920s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5650s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5643s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5905s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5643s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2176s - [COUNTERS] Fortran Other ( 0 ) : 0.0354s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3773s for 206659 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0542s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.0940s + [COUNTERS] Fortran Other ( 0 ) : 0.0350s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2538s for 206659 events => throughput is 8.14E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0540s for 16384 events => throughput is 3.04E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0095s for 16384 events => throughput is 1.73E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.09E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5656s for 16384 events => throughput is 6.39E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6520s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5656s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5658s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5282s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5658s for 16384 events => throughput is 6.39E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2750s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3435s for 195643 events => throughput is 5.70E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0801s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0323s for 16384 events => throughput is 5.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0602s for 195643 events => throughput is 3.25E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.1526s + [COUNTERS] Fortran Other ( 0 ) : 0.0368s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2195s for 195643 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0695s for 49152 events => throughput is 7.07E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0804s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0323s for 16384 events => throughput is 5.07E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0601s for 195643 events => throughput is 3.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7080s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5861s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5664s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8003s - [COUNTERS] Fortran Other ( 0 ) : 0.0485s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6761s for 370750 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1139s for 16384 events => throughput is 1.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1773s for 370750 events => throughput is 2.09E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.5690s + [COUNTERS] Fortran Other ( 0 ) : 0.0480s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4447s for 370750 events => throughput is 8.34E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1140s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1771s for 370750 events => throughput is 2.09E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5658s for 16384 events => throughput is 6.39E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2345s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5658s for 16384 events => throughput is 6.39E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5668s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0022s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5668s for 16384 events => throughput is 6.38E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.8051 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.2744 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/G42/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7939s - [COUNTERS] Fortran Other ( 0 ) : 0.0894s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5098s for 974583 events => throughput is 6.45E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0685s for 49152 events => throughput is 7.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.2634s + [COUNTERS] Fortran Other ( 0 ) : 0.0884s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9822s for 974583 events => throughput is 9.92E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.19E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0588s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0942s for 974583 events => throughput is 1.03E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0940s for 974583 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8098s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9841s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8098s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8095s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4539s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8095s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 56.6348 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 52.0061 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.4517s - [COUNTERS] Fortran Other ( 0 ) : 0.0776s + [COUNTERS] PROGRAM TOTAL : 3.9909s + [COUNTERS] Fortran Other ( 0 ) : 0.0771s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4227s for 850849 events => throughput is 5.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1089s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0382s for 16384 events => throughput is 4.29E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 850849 events => throughput is 1.27E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9676s for 850849 events => throughput is 8.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1084s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0369s for 16384 events => throughput is 4.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0673s for 850849 events => throughput is 1.26E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5739s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8778s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5739s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5705s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4203s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5705s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.3843s - [COUNTERS] Fortran Other ( 0 ) : 0.0732s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4049s for 778343 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0756s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0889s for 16384 events => throughput is 1.84E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0284s for 16384 events => throughput is 5.76E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0548s for 778343 events => throughput is 1.42E+07 events/s + [COUNTERS] PROGRAM TOTAL : 3.9387s + [COUNTERS] Fortran Other ( 0 ) : 0.0714s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9600s for 778343 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0886s for 16384 events => throughput is 1.85E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0285s for 16384 events => throughput is 5.74E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0545s for 778343 events => throughput is 1.43E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5713s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8130s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5713s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5721s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3666s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5721s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.9253s - [COUNTERS] Fortran Other ( 0 ) : 0.1005s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9528s for 1190413 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0863s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.3043s + [COUNTERS] Fortran Other ( 0 ) : 0.1004s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3307s for 1190413 events => throughput is 8.95E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0859s for 16384 events => throughput is 1.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0107s for 16384 events => throughput is 1.53E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0443s for 1190413 events => throughput is 2.69E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0442s for 1190413 events => throughput is 2.69E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3584s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5669s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5686s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7357s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5686s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5018s - [COUNTERS] Fortran Other ( 0 ) : 0.0453s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5658s for 314106 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0550s for 16384 events => throughput is 2.98E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3128s + [COUNTERS] Fortran Other ( 0 ) : 0.0449s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3793s for 314106 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0549s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0401s for 16384 events => throughput is 4.08E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0621s for 314106 events => throughput is 5.06E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0618s for 314106 events => throughput is 5.08E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5699s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9319s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5699s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5680s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7449s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5680s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.6063s - [COUNTERS] Fortran Other ( 0 ) : 0.0821s + [COUNTERS] PROGRAM TOTAL : 4.1203s + [COUNTERS] Fortran Other ( 0 ) : 0.0813s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4753s for 882930 events => throughput is 5.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1097s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1288s for 882930 events => throughput is 6.86E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9908s for 882930 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1086s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1280s for 882930 events => throughput is 6.90E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5680s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0384s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5680s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5693s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5510s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5693s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3436s - [COUNTERS] Fortran Other ( 0 ) : 0.0340s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3388s for 187611 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0821s for 16384 events => throughput is 2.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0610s for 16384 events => throughput is 2.68E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0949s for 187611 events => throughput is 1.98E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.2302s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2280s for 187611 events => throughput is 8.23E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0613s for 16384 events => throughput is 2.67E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0954s for 187611 events => throughput is 1.97E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5690s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7746s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5690s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5681s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6620s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5681s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.9761s - [COUNTERS] Fortran Other ( 0 ) : 0.1364s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.7957s for 1696178 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0697s for 49152 events => throughput is 7.05E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0876s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0826s for 16384 events => throughput is 1.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1438s for 1696178 events => throughput is 1.18E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s + [COUNTERS] PROGRAM TOTAL : 5.0760s + [COUNTERS] Fortran Other ( 0 ) : 0.1353s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8982s for 1696178 events => throughput is 8.94E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0874s for 16384 events => throughput is 1.87E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0834s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1427s for 1696178 events => throughput is 1.19E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5734s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 3.4027s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5734s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5735s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.5026s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5735s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2198s - [COUNTERS] Fortran Other ( 0 ) : 0.0317s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2679s for 138227 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0558s for 16384 events => throughput is 2.94E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1401s + [COUNTERS] Fortran Other ( 0 ) : 0.0315s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1867s for 138227 events => throughput is 7.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0538s for 16384 events => throughput is 3.04E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0750s for 138227 events => throughput is 1.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5724s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6475s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5724s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5744s for 16384 events => throughput is 6.36E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5656s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5744s for 16384 events => throughput is 6.36E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3178s - [COUNTERS] Fortran Other ( 0 ) : 0.0393s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3676s for 215899 events => throughput is 5.87E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0768s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1876s + [COUNTERS] Fortran Other ( 0 ) : 0.0388s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2399s for 215899 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0301s for 16384 events => throughput is 5.44E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0663s for 215899 events => throughput is 3.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7467s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5688s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6188s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5688s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3738s - [COUNTERS] Fortran Other ( 0 ) : 0.0392s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4935s for 254421 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0342s for 254421 events => throughput is 7.44E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.2245s + [COUNTERS] Fortran Other ( 0 ) : 0.0389s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3420s for 254421 events => throughput is 7.44E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0541s for 16384 events => throughput is 3.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0209s for 16384 events => throughput is 7.85E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0341s for 254421 events => throughput is 7.47E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5692s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8047s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5692s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6534s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.9378s - [COUNTERS] Fortran Other ( 0 ) : 0.0876s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8186s for 1024423 events => throughput is 5.63E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] PROGRAM TOTAL : 4.3773s + [COUNTERS] Fortran Other ( 0 ) : 0.0864s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2600s for 1024423 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1328s for 1024423 events => throughput is 7.71E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5700s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3678s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5700s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5699s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8074s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5699s for 16384 events => throughput is 6.38E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2876s - [COUNTERS] Fortran Other ( 0 ) : 0.0373s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3358s for 193396 events => throughput is 5.76E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1698s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2199s for 193396 events => throughput is 8.80E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0960s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0315s for 16384 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0599s for 193396 events => throughput is 3.23E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0946s for 16384 events => throughput is 1.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0315s for 16384 events => throughput is 5.20E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0602s for 193396 events => throughput is 3.21E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5715s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7161s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5715s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5988s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5711s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7351s - [COUNTERS] Fortran Other ( 0 ) : 0.0492s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6524s for 362054 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0561s for 16384 events => throughput is 2.92E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0960s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1451s for 362054 events => throughput is 2.49E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s + [COUNTERS] PROGRAM TOTAL : 3.5180s + [COUNTERS] Fortran Other ( 0 ) : 0.0487s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4361s for 362054 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0559s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0962s for 16384 events => throughput is 1.70E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1455s for 362054 events => throughput is 2.49E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0117s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5720s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1631s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5720s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5716s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9464s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5716s for 16384 events => throughput is 6.37E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G76/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4547s - [COUNTERS] Fortran Other ( 0 ) : 0.0452s + [COUNTERS] PROGRAM TOTAL : 3.2988s + [COUNTERS] Fortran Other ( 0 ) : 0.0444s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4618s for 265638 events => throughput is 5.75E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0768s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0500s for 16384 events => throughput is 3.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0887s for 265638 events => throughput is 2.99E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3059s for 265638 events => throughput is 8.68E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0500s for 16384 events => throughput is 3.28E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0894s for 265638 events => throughput is 2.97E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5686s for 16384 events => throughput is 6.38E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8861s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5686s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5687s for 16384 events => throughput is 6.38E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7301s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5687s for 16384 events => throughput is 6.38E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 2.4454 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 2.2949 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4340s + [COUNTERS] PROGRAM TOTAL : 2.2836s [COUNTERS] Fortran Other ( 0 ) : 0.0412s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4911s for 259134 events => throughput is 5.28E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0424s for 16384 events => throughput is 3.86E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0318s for 16384 events => throughput is 5.15E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3401s for 259134 events => throughput is 7.62E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0429s for 16384 events => throughput is 3.82E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.17E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 259134 events => throughput is 5.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.6274s for 16384 events => throughput is 1.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8066s - [COUNTERS] OVERALL MEs ( 32 ) : 1.6274s for 16384 events => throughput is 1.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.6280s for 16384 events => throughput is 1.01E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6556s + [COUNTERS] OVERALL MEs ( 32 ) : 1.6280s for 16384 events => throughput is 1.01E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 5.8142 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 5.3916 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4331s - [COUNTERS] Fortran Other ( 0 ) : 0.0349s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3395s for 187490 events => throughput is 5.52E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0707s for 49152 events => throughput is 6.95E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3237s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2312s for 187490 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0673s for 16384 events => throughput is 2.43E+05 events/s INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0077s for 16384 events => throughput is 2.12E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0167s for 187490 events => throughput is 1.12E+07 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0078s for 16384 events => throughput is 2.10E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0166s for 187490 events => throughput is 1.13E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8109s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6222s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8109s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8114s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5123s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8114s for 16384 events => throughput is 2.02E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5124s - [COUNTERS] Fortran Other ( 0 ) : 0.0398s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4122s for 229909 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.77E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0178s for 16384 events => throughput is 9.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0303s for 229909 events => throughput is 7.59E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s + [COUNTERS] PROGRAM TOTAL : 1.3876s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2819s for 229909 events => throughput is 8.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0178s for 16384 events => throughput is 9.22E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0358s for 229909 events => throughput is 6.42E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8146s for 16384 events => throughput is 2.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6978s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8146s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8133s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5743s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8133s for 16384 events => throughput is 2.01E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4305s - [COUNTERS] Fortran Other ( 0 ) : 0.0335s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0425s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3248s for 170163 events => throughput is 5.24E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0458s for 16384 events => throughput is 3.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0237s for 16384 events => throughput is 6.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0353s for 170163 events => throughput is 4.82E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s + [COUNTERS] PROGRAM TOTAL : 1.3305s + [COUNTERS] Fortran Other ( 0 ) : 0.0333s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2259s for 170163 events => throughput is 7.53E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.02E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0456s for 16384 events => throughput is 3.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0238s for 16384 events => throughput is 6.89E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0353s for 170163 events => throughput is 4.83E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8120s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6185s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8120s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5181s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4026s - [COUNTERS] Fortran Other ( 0 ) : 0.0325s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2829s for 155440 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0693s for 16384 events => throughput is 2.36E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3134s + [COUNTERS] Fortran Other ( 0 ) : 0.0323s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1928s for 155440 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0697s for 16384 events => throughput is 2.35E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0204s for 16384 events => throughput is 8.02E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0311s for 155440 events => throughput is 5.00E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8120s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5906s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8120s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0310s for 155440 events => throughput is 5.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8124s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5010s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8124s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 18.1383 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 17.5909 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.4529s - [COUNTERS] Fortran Other ( 0 ) : 0.0374s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0410s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3646s for 193303 events => throughput is 5.30E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0804s for 49152 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0045s for 16384 events => throughput is 3.64E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0129s for 193303 events => throughput is 1.50E+07 events/s + [COUNTERS] PROGRAM TOTAL : 4.3381s + [COUNTERS] Fortran Other ( 0 ) : 0.0369s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2469s for 193303 events => throughput is 7.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0801s for 49152 events => throughput is 6.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0045s for 16384 events => throughput is 3.61E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 193303 events => throughput is 1.49E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0114s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 3.8128s for 16384 events => throughput is 4.30E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6402s - [COUNTERS] OVERALL MEs ( 32 ) : 3.8128s for 16384 events => throughput is 4.30E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 3.8168s for 16384 events => throughput is 4.29E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5214s + [COUNTERS] OVERALL MEs ( 32 ) : 3.8168s for 16384 events => throughput is 4.29E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G21/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.8559s - [COUNTERS] Fortran Other ( 0 ) : 0.0535s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6779s for 430212 events => throughput is 6.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1025s for 16384 events => throughput is 1.60E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0174s for 16384 events => throughput is 9.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0332s for 430212 events => throughput is 1.29E+07 events/s + [COUNTERS] PROGRAM TOTAL : 4.6176s + [COUNTERS] Fortran Other ( 0 ) : 0.0532s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4446s for 430212 events => throughput is 9.68E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1028s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0332s for 430212 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 3.8044s for 16384 events => throughput is 4.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0515s - [COUNTERS] OVERALL MEs ( 32 ) : 3.8044s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 3.7995s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8181s + [COUNTERS] OVERALL MEs ( 32 ) : 3.7995s for 16384 events => throughput is 4.31E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.3954s - [COUNTERS] Fortran Other ( 0 ) : 0.0320s + [COUNTERS] PROGRAM TOTAL : 4.3055s + [COUNTERS] Fortran Other ( 0 ) : 0.0316s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2877s for 154293 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0807s for 49152 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0777s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0099s for 16384 events => throughput is 1.65E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0181s for 154293 events => throughput is 8.54E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1983s for 154293 events => throughput is 7.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0802s for 49152 events => throughput is 6.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0789s for 16384 events => throughput is 2.08E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0100s for 16384 events => throughput is 1.65E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 3.8019s for 16384 events => throughput is 4.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5935s - [COUNTERS] OVERALL MEs ( 32 ) : 3.8019s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 3.8015s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5040s + [COUNTERS] OVERALL MEs ( 32 ) : 3.8015s for 16384 events => throughput is 4.31E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.3977s - [COUNTERS] Fortran Other ( 0 ) : 0.0324s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3299s for 159370 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.2926s + [COUNTERS] Fortran Other ( 0 ) : 0.0318s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2260s for 159370 events => throughput is 7.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0053s for 16384 events => throughput is 3.08E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.23E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0114s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.22E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 3.7982s for 16384 events => throughput is 4.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5995s - [COUNTERS] OVERALL MEs ( 32 ) : 3.7982s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 3.7977s for 16384 events => throughput is 4.31E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4949s + [COUNTERS] OVERALL MEs ( 32 ) : 3.7977s for 16384 events => throughput is 4.31E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 4.5820 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 4.1753 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5074s + [COUNTERS] PROGRAM TOTAL : 1.3835s [COUNTERS] Fortran Other ( 0 ) : 0.0360s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3846s for 212440 events => throughput is 5.52E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2601s for 212440 events => throughput is 8.17E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0681s for 16384 events => throughput is 2.41E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0349s for 16384 events => throughput is 4.70E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0201s for 16384 events => throughput is 8.15E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.58E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0682s for 16384 events => throughput is 2.40E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0203s for 16384 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.59E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8107s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6967s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8107s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8115s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5720s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8115s for 16384 events => throughput is 2.02E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5428s - [COUNTERS] Fortran Other ( 0 ) : 0.0412s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4546s for 250568 events => throughput is 5.51E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3944s + [COUNTERS] Fortran Other ( 0 ) : 0.0415s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3058s for 250568 events => throughput is 8.19E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0709s for 49152 events => throughput is 6.93E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0431s for 16384 events => throughput is 3.80E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.77E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0125s for 16384 events => throughput is 1.31E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0242s for 250568 events => throughput is 1.04E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0241s for 250568 events => throughput is 1.04E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0086s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7305s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5827s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5047s - [COUNTERS] Fortran Other ( 0 ) : 0.0365s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4111s for 227751 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0708s for 49152 events => throughput is 6.94E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0681s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0059s for 16384 events => throughput is 2.77E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0156s for 227751 events => throughput is 1.46E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.3686s + [COUNTERS] Fortran Other ( 0 ) : 0.0364s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2779s for 227751 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0675s for 16384 events => throughput is 2.43E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0060s for 16384 events => throughput is 2.75E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.46E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6931s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8116s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8098s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5587s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8098s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 1.4733 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 1.3650 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4627s - [COUNTERS] Fortran Other ( 0 ) : 0.0333s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3559s for 184243 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0445s for 16384 events => throughput is 3.68E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.57E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0380s for 184243 events => throughput is 4.85E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.3534s + [COUNTERS] Fortran Other ( 0 ) : 0.0329s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2482s for 184243 events => throughput is 7.42E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0437s for 16384 events => throughput is 3.75E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0250s for 16384 events => throughput is 6.56E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0379s for 184243 events => throughput is 4.86E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0081s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8140s for 16384 events => throughput is 2.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6488s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8140s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8130s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5405s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8130s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 3.8721 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 3.2767 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/G14/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8615s - [COUNTERS] Fortran Other ( 0 ) : 0.0982s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8757s for 1143085 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0569s for 16384 events => throughput is 2.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0108s for 16384 events => throughput is 1.52E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0434s for 1143085 events => throughput is 2.63E+07 events/s + [COUNTERS] PROGRAM TOTAL : 3.2659s + [COUNTERS] Fortran Other ( 0 ) : 0.0968s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2827s for 1143085 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0566s for 16384 events => throughput is 2.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0109s for 16384 events => throughput is 1.51E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1143085 events => throughput is 2.66E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.6235s for 16384 events => throughput is 1.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2380s - [COUNTERS] OVERALL MEs ( 32 ) : 1.6235s for 16384 events => throughput is 1.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.6231s for 16384 events => throughput is 1.01E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6428s + [COUNTERS] OVERALL MEs ( 32 ) : 1.6231s for 16384 events => throughput is 1.01E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 17.8458 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 17.4428 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.1056s - [COUNTERS] Fortran Other ( 0 ) : 0.0461s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6186s for 332018 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0531s for 16384 events => throughput is 3.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0786s for 332018 events => throughput is 4.22E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] PROGRAM TOTAL : 5.9162s + [COUNTERS] Fortran Other ( 0 ) : 0.0453s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4318s for 332018 events => throughput is 7.69E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0789s for 332018 events => throughput is 4.21E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0912s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0144s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0912s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0887s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8275s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0887s for 16384 events => throughput is 3.22E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.9053s - [COUNTERS] Fortran Other ( 0 ) : 0.0345s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3403s for 183011 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0777s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0630s for 16384 events => throughput is 2.60E+05 events/s + [COUNTERS] PROGRAM TOTAL : 5.8026s + [COUNTERS] Fortran Other ( 0 ) : 0.0347s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2360s for 183011 events => throughput is 7.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0790s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0628s for 16384 events => throughput is 2.61E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 183011 events => throughput is 1.84E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1254s for 16384 events => throughput is 3.20E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7799s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1254s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1241s for 16384 events => throughput is 3.20E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6786s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1241s for 16384 events => throughput is 3.20E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 5.8073s - [COUNTERS] Fortran Other ( 0 ) : 0.0363s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3473s for 193329 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0696s for 49152 events => throughput is 7.06E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 5.6966s + [COUNTERS] Fortran Other ( 0 ) : 0.0368s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2336s for 193329 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0354s for 16384 events => throughput is 4.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0610s for 193329 events => throughput is 3.17E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0355s for 16384 events => throughput is 4.62E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0607s for 193329 events => throughput is 3.19E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.0902s for 16384 events => throughput is 3.22E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7171s - [COUNTERS] OVERALL MEs ( 32 ) : 5.0902s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.0946s for 16384 events => throughput is 3.22E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6020s + [COUNTERS] OVERALL MEs ( 32 ) : 5.0946s for 16384 events => throughput is 3.22E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 1.5601 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 1.4168 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5485s - [COUNTERS] Fortran Other ( 0 ) : 0.0398s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4372s for 243014 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0667s for 49152 events => throughput is 7.37E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.73E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0257s for 16384 events => throughput is 6.37E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 243014 events => throughput is 5.89E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s + [COUNTERS] PROGRAM TOTAL : 1.4060s + [COUNTERS] Fortran Other ( 0 ) : 0.0392s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2943s for 243014 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0669s for 49152 events => throughput is 7.35E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0434s for 16384 events => throughput is 3.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.35E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 243014 events => throughput is 5.90E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8100s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7385s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8100s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8107s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5952s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8107s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 4.9629 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 4.7993 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4815s - [COUNTERS] Fortran Other ( 0 ) : 0.0319s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2759s for 152585 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0797s for 49152 events => throughput is 6.17E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0822s for 16384 events => throughput is 1.99E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.3893s + [COUNTERS] Fortran Other ( 0 ) : 0.0309s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1863s for 152585 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0800s for 49152 events => throughput is 6.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0047s for 16384 events => throughput is 3.46E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0122s for 152585 events => throughput is 1.25E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0048s for 16384 events => throughput is 3.42E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0121s for 152585 events => throughput is 1.26E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0114s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.9076s for 16384 events => throughput is 8.59E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5738s - [COUNTERS] OVERALL MEs ( 32 ) : 1.9076s for 16384 events => throughput is 8.59E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.9070s for 16384 events => throughput is 8.59E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4822s + [COUNTERS] OVERALL MEs ( 32 ) : 1.9070s for 16384 events => throughput is 8.59E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G62/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4619s - [COUNTERS] Fortran Other ( 0 ) : 0.0292s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2222s for 121146 events => throughput is 5.45E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0805s for 49152 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0832s for 16384 events => throughput is 1.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0206s for 16384 events => throughput is 7.96E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0321s for 121146 events => throughput is 3.77E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.3907s + [COUNTERS] Fortran Other ( 0 ) : 0.0294s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1503s for 121146 events => throughput is 8.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0797s for 49152 events => throughput is 6.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0848s for 16384 events => throughput is 1.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 7.98E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 121146 events => throughput is 3.76E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0115s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.9056s for 16384 events => throughput is 8.60E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5563s - [COUNTERS] OVERALL MEs ( 32 ) : 1.9056s for 16384 events => throughput is 8.60E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.9060s for 16384 events => throughput is 8.60E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4847s + [COUNTERS] OVERALL MEs ( 32 ) : 1.9060s for 16384 events => throughput is 8.60E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 6.1702 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 5.9696 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 6.1592s - [COUNTERS] Fortran Other ( 0 ) : 0.0421s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6637s for 329671 events => throughput is 4.97E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0505s for 16384 events => throughput is 3.24E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0815s for 329671 events => throughput is 4.04E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0118s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 5.1007s for 16384 events => throughput is 3.21E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0585s - [COUNTERS] OVERALL MEs ( 32 ) : 5.1007s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] PROGRAM TOTAL : 5.9584s + [COUNTERS] Fortran Other ( 0 ) : 0.0418s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4633s for 329671 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 49152 events => throughput is 6.29E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0506s for 16384 events => throughput is 3.24E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0812s for 329671 events => throughput is 4.06E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0119s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 5.1004s for 16384 events => throughput is 3.21E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8580s + [COUNTERS] OVERALL MEs ( 32 ) : 5.1004s for 16384 events => throughput is 3.21E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 1.6166 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 1.4664 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/G7/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6052s - [COUNTERS] Fortran Other ( 0 ) : 0.0403s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4918s for 255151 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.89E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0410s for 16384 events => throughput is 3.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0509s for 255151 events => throughput is 5.01E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.4550s + [COUNTERS] Fortran Other ( 0 ) : 0.0396s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3426s for 255151 events => throughput is 7.45E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.90E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0412s for 16384 events => throughput is 3.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0507s for 255151 events => throughput is 5.04E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.7798s for 16384 events => throughput is 2.10E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8254s - [COUNTERS] OVERALL MEs ( 32 ) : 0.7798s for 16384 events => throughput is 2.10E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.7799s for 16384 events => throughput is 2.10E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6751s + [COUNTERS] OVERALL MEs ( 32 ) : 0.7799s for 16384 events => throughput is 2.10E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 2.8447 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 2.6279 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3504s - [COUNTERS] Fortran Other ( 0 ) : 0.0342s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2934s for 159224 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.04E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0444s for 16384 events => throughput is 3.69E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2562s + [COUNTERS] Fortran Other ( 0 ) : 0.0338s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1978s for 159224 events => throughput is 8.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0445s for 16384 events => throughput is 3.68E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.04E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0132s for 159224 events => throughput is 1.20E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0084s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.03E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0132s for 159224 events => throughput is 1.21E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8055s for 16384 events => throughput is 2.03E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5448s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8055s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8065s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4496s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8065s for 16384 events => throughput is 2.03E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4753s - [COUNTERS] Fortran Other ( 0 ) : 0.0343s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3938s for 201854 events => throughput is 5.13E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.3528s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2725s for 201854 events => throughput is 7.41E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0698s for 49152 events => throughput is 7.04E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0427s for 16384 events => throughput is 3.84E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0164s for 16384 events => throughput is 9.97E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.31E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0429s for 16384 events => throughput is 3.82E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0164s for 16384 events => throughput is 9.98E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.33E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0082s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8067s for 16384 events => throughput is 2.03E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6685s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8067s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8052s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5475s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8052s for 16384 events => throughput is 2.03E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 2.4087 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 2.2561 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3978s - [COUNTERS] Fortran Other ( 0 ) : 0.0428s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4967s for 268443 events => throughput is 5.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0697s for 49152 events => throughput is 7.06E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0093s for 16384 events => throughput is 1.77E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0204s for 268443 events => throughput is 1.31E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.2451s + [COUNTERS] Fortran Other ( 0 ) : 0.0419s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3413s for 268443 events => throughput is 7.87E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0094s for 16384 events => throughput is 1.75E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0206s for 268443 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.6314s for 16384 events => throughput is 1.00E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7663s - [COUNTERS] OVERALL MEs ( 32 ) : 1.6314s for 16384 events => throughput is 1.00E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.6338s for 16384 events => throughput is 1.00E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6113s + [COUNTERS] OVERALL MEs ( 32 ) : 1.6338s for 16384 events => throughput is 1.00E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 2.2279 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 2.1314 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2172s - [COUNTERS] Fortran Other ( 0 ) : 0.0328s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3152s for 168484 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0664s for 16384 events => throughput is 2.47E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0032s for 16384 events => throughput is 5.15E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.1199s + [COUNTERS] Fortran Other ( 0 ) : 0.0324s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2169s for 168484 events => throughput is 7.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0665s for 16384 events => throughput is 2.46E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0033s for 16384 events => throughput is 5.01E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.58E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0083s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.6344s for 16384 events => throughput is 1.00E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5828s - [COUNTERS] OVERALL MEs ( 32 ) : 1.6344s for 16384 events => throughput is 1.00E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.6351s for 16384 events => throughput is 1.00E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4847s + [COUNTERS] OVERALL MEs ( 32 ) : 1.6351s for 16384 events => throughput is 1.00E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 428.3544 seconds -__CUDACPP_DEBUG: gen_ximprove.launch finished in 428.9209 seconds -__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 428.9214 seconds +__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 403.2202 seconds +__CUDACPP_DEBUG: gen_ximprove.launch finished in 403.7747 seconds +__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 403.7753 seconds __CUDACPP_DEBUG: GridPackCmd.launch (3a) combine_events combine_events __CUDACPP_DEBUG: GridPackCmd.launch (3b) store_events @@ -2117,9 +2117,9 @@ store_events INFO: No version of lhapdf. Can not run systematics computation decay_events -from_cards -__CUDACPP_DEBUG: GridPackCmd.launch finished in 431.5723 seconds +__CUDACPP_DEBUG: GridPackCmd.launch finished in 406.4365 seconds __CUDACPP_DEBUG: GridPackCmd.__init__ back from self.launch DONE write ./events.lhe.gz -END: Thu Aug 22 03:46:40 PM CEST 2024 -ELAPSED: 432 seconds +END: Thu Aug 22 05:00:54 PM CEST 2024 +ELAPSED: 407 seconds diff --git a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppsse4/output.txt b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppsse4/output.txt index 7289d33425..80b8281d46 100644 --- a/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppsse4/output.txt +++ b/epochX/cudacpp/tlau/fromgridpacks/pp_dy3j.mad/cppsse4/output.txt @@ -1,91 +1,91 @@ -START: Thu Aug 22 03:46:57 PM CEST 2024 +START: Thu Aug 22 05:01:11 PM CEST 2024 On itgold91.cern.ch [CPU: Intel(R) Xeon(R) Gold 6326 CPU (nproc=32)] [GPU: none]: CUDACPP_RUNTIME_DISABLEFPE is set -CUDACPP_RUNTIME_SKIPXBINCHECKS is not set -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp -lrwxrwxrwx. 1 avalassi zg 35 Aug 22 15:46 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +CUDACPP_RUNTIME_SKIPXBINCHECKS is set +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dc_epemgdc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dc_taptamgdc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dd_epemgdd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dd_taptamgdd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_epemggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_epemgssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_taptamggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_taptamgssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ddx_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ds_epemgds/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ds_taptamgds/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dsx_epemgdsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dsx_taptamgdsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dux_epemgdux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dux_taptamgdux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxcx_epemgdxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxcx_taptamgdxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxdx_epemgdxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxdx_taptamgdxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxsx_epemgdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_dxsx_taptamgdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_epemdddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_epemdssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_epemggd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_epemudux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_taptamdddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_taptamdssx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_taptamggd/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gd_taptamudux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_epemddxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_epemggdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_epemsdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_epemuuxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_taptamddxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_taptamggdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_taptamsdxsx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gdx_taptamuuxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gg_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gg_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gg_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gg_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_epemggu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_epemuccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_epemuddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_epemuuux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_taptamggu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_taptamuccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_taptamuddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gu_taptamuuux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_epemcuxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_epemduxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_epemggux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_epemuuxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_taptamcuxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_taptamduxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_taptamggux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_gux_taptamuuxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uc_epemguc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uc_taptamguc/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ucx_epemgucx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ucx_taptamgucx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ud_epemgud/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_ud_taptamgud/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_udx_epemgudx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_udx_taptamgudx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uu_epemguu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uu_taptamguu/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_epemgccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_epemgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_epemggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_epemguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_taptamgccx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_taptamgddx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_taptamggg/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uux_taptamguux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxcx_epemguxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxcx_taptamguxcx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxdx_epemguxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxdx_taptamguxdx/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxux_epemguxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp +lrwxrwxrwx. 1 avalassi zg 35 Aug 22 17:01 madevent/SubProcesses/P0_uxux_taptamguxux/madevent -> build.sse4_m_inl0_hrd0/madevent_cpp Now generating 100 events with random seed 21 and granularity 1 ************************************************************ * * @@ -211,1901 +211,1901 @@ __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event starting INFO: need to improve 108 channels __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 30.2843 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' in 28.0222 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9981s + [COUNTERS] PROGRAM TOTAL : 1.8944s [COUNTERS] Fortran Other ( 0 ) : 0.0340s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3249s for 176708 events => throughput is 5.44E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2197s for 176708 events => throughput is 8.04E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0771s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0463s for 16384 events => throughput is 3.53E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0463s for 16384 events => throughput is 3.54E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0684s for 176708 events => throughput is 2.58E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2870s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7111s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2870s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2874s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6070s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2874s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2171s + [COUNTERS] PROGRAM TOTAL : 2.0221s [COUNTERS] Fortran Other ( 0 ) : 0.0469s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6095s for 337001 events => throughput is 5.53E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4121s for 337001 events => throughput is 8.18E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0215s for 16384 events => throughput is 7.61E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0377s for 337001 events => throughput is 8.93E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2875s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9296s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2875s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.05E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0215s for 16384 events => throughput is 7.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0377s for 337001 events => throughput is 8.94E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2898s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7324s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2898s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0919s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3545s for 196960 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0833s for 16384 events => throughput is 1.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0671s for 16384 events => throughput is 2.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1031s for 196960 events => throughput is 1.91E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9745s + [COUNTERS] Fortran Other ( 0 ) : 0.0356s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2400s for 196960 events => throughput is 8.21E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0669s for 16384 events => throughput is 2.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1049s for 196960 events => throughput is 1.88E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2874s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8045s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2874s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6861s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2641s - [COUNTERS] Fortran Other ( 0 ) : 0.0426s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6266s for 324156 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0745s + [COUNTERS] Fortran Other ( 0 ) : 0.0428s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4372s for 324156 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0380s for 16384 events => throughput is 4.31E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0557s for 324156 events => throughput is 5.82E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0381s for 16384 events => throughput is 4.30E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0558s for 324156 events => throughput is 5.81E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2867s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9774s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2867s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2857s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7888s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2857s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9545s - [COUNTERS] Fortran Other ( 0 ) : 0.0356s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3051s for 176248 events => throughput is 5.78E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0825s for 16384 events => throughput is 1.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0294s for 16384 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0577s for 176248 events => throughput is 3.05E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.8433s + [COUNTERS] Fortran Other ( 0 ) : 0.0360s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2008s for 176248 events => throughput is 8.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0293s for 16384 events => throughput is 5.60E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0574s for 176248 events => throughput is 3.07E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2914s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6631s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2914s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2887s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5546s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2887s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8703s - [COUNTERS] Fortran Other ( 0 ) : 0.0310s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2504s for 128162 events => throughput is 5.12E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0537s for 16384 events => throughput is 3.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0358s for 16384 events => throughput is 4.57E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0500s for 128162 events => throughput is 2.56E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.7925s + [COUNTERS] Fortran Other ( 0 ) : 0.0312s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1736s for 128162 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0775s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0499s for 128162 events => throughput is 2.57E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2892s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5812s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2892s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5040s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G2/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9073s - [COUNTERS] Fortran Other ( 0 ) : 0.0759s + [COUNTERS] PROGRAM TOTAL : 2.5207s + [COUNTERS] Fortran Other ( 0 ) : 0.0672s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2221s for 680231 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8458s for 680231 events => throughput is 8.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0844s for 16384 events => throughput is 1.94E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.81E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0239s for 16384 events => throughput is 6.85E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0484s for 680231 events => throughput is 1.41E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2914s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6159s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2914s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2902s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2305s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2902s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0598s - [COUNTERS] Fortran Other ( 0 ) : 0.0405s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3885s for 227876 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0769s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0333s for 16384 events => throughput is 4.92E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0729s for 227876 events => throughput is 3.12E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9266s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2544s for 227876 events => throughput is 8.96E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0790s for 81920 events => throughput is 1.04E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0763s for 16384 events => throughput is 2.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0332s for 16384 events => throughput is 4.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 227876 events => throughput is 3.14E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2865s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7733s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2865s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2871s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6395s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2871s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1045s - [COUNTERS] Fortran Other ( 0 ) : 0.0389s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5014s for 258529 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0531s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0240s for 16384 events => throughput is 6.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9501s + [COUNTERS] Fortran Other ( 0 ) : 0.0390s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3493s for 258529 events => throughput is 7.40E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0524s for 16384 events => throughput is 3.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.81E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0384s for 258529 events => throughput is 6.74E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2880s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8165s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2880s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2859s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6642s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2859s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G75/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2209s - [COUNTERS] Fortran Other ( 0 ) : 0.0441s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5315s for 288195 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0580s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0816s for 288195 events => throughput is 3.53E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2893s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9316s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2893s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] PROGRAM TOTAL : 2.0455s + [COUNTERS] Fortran Other ( 0 ) : 0.0453s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3556s for 288195 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0580s for 16384 events => throughput is 2.83E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0815s for 288195 events => throughput is 3.54E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2890s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7565s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2890s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4934s - [COUNTERS] Fortran Other ( 0 ) : 0.0495s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6514s for 362045 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0636s for 16384 events => throughput is 2.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1098s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1711s for 362045 events => throughput is 2.12E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 2.2775s + [COUNTERS] Fortran Other ( 0 ) : 0.0489s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4355s for 362045 events => throughput is 8.31E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0642s for 16384 events => throughput is 2.55E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1095s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1705s for 362045 events => throughput is 2.12E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 1.2877s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2057s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9898s [COUNTERS] OVERALL MEs ( 32 ) : 1.2877s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0009s - [COUNTERS] Fortran Other ( 0 ) : 0.0402s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3293s for 203191 events => throughput is 6.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0367s for 16384 events => throughput is 4.47E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0673s for 203191 events => throughput is 3.02E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.8793s + [COUNTERS] Fortran Other ( 0 ) : 0.0396s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2096s for 203191 events => throughput is 9.70E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0366s for 16384 events => throughput is 4.47E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0669s for 203191 events => throughput is 3.04E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2882s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7126s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2882s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2875s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5918s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2875s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9307s - [COUNTERS] Fortran Other ( 0 ) : 0.0364s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3794s for 205739 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0546s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.8038s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2530s for 205739 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0554s for 16384 events => throughput is 2.96E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0057s for 16384 events => throughput is 2.89E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0145s for 205739 events => throughput is 1.42E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0146s for 205739 events => throughput is 1.41E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2884s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6423s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2884s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2880s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5159s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2880s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0493s - [COUNTERS] Fortran Other ( 0 ) : 0.0599s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3657s for 214038 events => throughput is 5.85E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0696s for 49152 events => throughput is 7.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9005s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2396s for 214038 events => throughput is 8.93E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.13E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0672s for 214038 events => throughput is 3.18E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0674s for 214038 events => throughput is 3.17E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2893s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7599s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2893s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2888s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6118s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2888s for 16384 events => throughput is 1.27E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 6.8957 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' in 6.4102 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4203s - [COUNTERS] Fortran Other ( 0 ) : 0.0498s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6179s for 344023 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0831s for 81920 events => throughput is 9.86E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0568s for 16384 events => throughput is 2.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1010s for 16384 events => throughput is 1.62E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1456s for 344023 events => throughput is 2.36E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.2167s + [COUNTERS] Fortran Other ( 0 ) : 0.0497s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4163s for 344023 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0833s for 81920 events => throughput is 9.83E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0566s for 16384 events => throughput is 2.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1008s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1451s for 344023 events => throughput is 2.37E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2838s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1365s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2838s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2823s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9344s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2823s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G43/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1811s - [COUNTERS] Fortran Other ( 0 ) : 0.0393s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4115s for 214181 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1356s for 212992 events => throughput is 1.57E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0594s for 16384 events => throughput is 2.76E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0709s for 16384 events => throughput is 2.31E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 214181 events => throughput is 2.16E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 2.0566s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2864s for 214181 events => throughput is 7.48E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1355s for 212992 events => throughput is 1.57E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0587s for 16384 events => throughput is 2.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0716s for 16384 events => throughput is 2.29E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0994s for 214181 events => throughput is 2.15E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2824s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8987s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2824s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2827s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7739s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2827s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/G56/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2666s - [COUNTERS] Fortran Other ( 0 ) : 0.0420s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5400s for 279555 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.1139s for 147456 events => throughput is 1.30E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0568s for 16384 events => throughput is 2.88E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0617s for 16384 events => throughput is 2.65E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0862s for 279555 events => throughput is 3.24E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.1099s + [COUNTERS] Fortran Other ( 0 ) : 0.0498s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3773s for 279555 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.1131s for 147456 events => throughput is 1.30E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0573s for 16384 events => throughput is 2.86E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0616s for 16384 events => throughput is 2.66E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0861s for 279555 events => throughput is 3.25E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2830s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9835s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2830s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2821s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8277s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2821s for 16384 events => throughput is 1.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uux_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 2.6481 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' in 2.2189 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/G67/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.6367s - [COUNTERS] Fortran Other ( 0 ) : 0.0757s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2723s for 814370 events => throughput is 6.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0794s for 49152 events => throughput is 6.19E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1108s for 16384 events => throughput is 1.48E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.2079s + [COUNTERS] Fortran Other ( 0 ) : 0.0754s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.8420s for 814370 events => throughput is 9.67E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0792s for 49152 events => throughput is 6.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1122s for 16384 events => throughput is 1.46E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0306s for 16384 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0601s for 814370 events => throughput is 1.36E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0304s for 16384 events => throughput is 5.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0592s for 814370 events => throughput is 1.38E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9250s for 16384 events => throughput is 1.77E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7117s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9250s for 16384 events => throughput is 1.77E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9266s for 16384 events => throughput is 1.77E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2813s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9266s for 16384 events => throughput is 1.77E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uxux_epemguxux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 19.0428 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' in 17.8844 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.7298s - [COUNTERS] Fortran Other ( 0 ) : 0.0811s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5449s for 933480 events => throughput is 6.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1030s for 16384 events => throughput is 1.59E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1005s for 16384 events => throughput is 1.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1599s for 933480 events => throughput is 5.84E+06 events/s + [COUNTERS] PROGRAM TOTAL : 4.2484s + [COUNTERS] Fortran Other ( 0 ) : 0.0818s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0659s for 933480 events => throughput is 8.76E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0774s for 49152 events => throughput is 6.35E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1016s for 16384 events => throughput is 1.61E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1002s for 16384 events => throughput is 1.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1590s for 933480 events => throughput is 5.87E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5799s for 16384 events => throughput is 6.35E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1499s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5799s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5796s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6688s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5796s for 16384 events => throughput is 6.35E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4825s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4231s for 226350 events => throughput is 5.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3564s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2917s for 226350 events => throughput is 7.76E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 49152 events => throughput is 6.33E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0799s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1219s for 226350 events => throughput is 1.86E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0800s for 16384 events => throughput is 2.05E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1218s for 226350 events => throughput is 1.86E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5828s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8997s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5828s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5884s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7680s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5884s for 16384 events => throughput is 6.33E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6480s + [COUNTERS] PROGRAM TOTAL : 3.4526s [COUNTERS] Fortran Other ( 0 ) : 0.0414s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6539s for 323984 events => throughput is 4.95E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 49152 events => throughput is 6.29E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0499s for 16384 events => throughput is 3.28E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0633s for 16384 events => throughput is 2.59E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0931s for 323984 events => throughput is 3.48E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4591s for 323984 events => throughput is 7.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0499s for 16384 events => throughput is 3.29E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0638s for 16384 events => throughput is 2.57E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0947s for 323984 events => throughput is 3.42E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5853s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0627s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5853s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5836s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8690s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5836s for 16384 events => throughput is 6.34E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7094s - [COUNTERS] Fortran Other ( 0 ) : 0.0423s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0427s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7136s for 355559 events => throughput is 4.98E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0514s for 16384 events => throughput is 3.19E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0622s for 16384 events => throughput is 2.64E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0932s for 355559 events => throughput is 3.82E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.4952s + [COUNTERS] Fortran Other ( 0 ) : 0.0422s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5011s for 355559 events => throughput is 7.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0502s for 16384 events => throughput is 3.26E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0622s for 16384 events => throughput is 2.63E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0928s for 355559 events => throughput is 3.83E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5851s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1242s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5851s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9102s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/G92/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.4296s - [COUNTERS] Fortran Other ( 0 ) : 0.0407s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4543s for 255849 events => throughput is 5.63E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0780s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0387s for 16384 events => throughput is 4.24E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0839s for 255849 events => throughput is 3.05E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.2887s + [COUNTERS] Fortran Other ( 0 ) : 0.0419s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3049s for 255849 events => throughput is 8.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0384s for 16384 events => throughput is 4.27E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0835s for 255849 events => throughput is 3.06E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5733s for 16384 events => throughput is 6.37E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8563s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5733s for 16384 events => throughput is 6.37E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5811s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7076s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5811s for 16384 events => throughput is 6.35E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 17.4219 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' in 15.7222 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.5353s - [COUNTERS] Fortran Other ( 0 ) : 0.0779s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4145s for 859290 events => throughput is 6.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1060s for 16384 events => throughput is 1.55E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0576s for 16384 events => throughput is 2.84E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0995s for 859290 events => throughput is 8.63E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 4.0823s + [COUNTERS] Fortran Other ( 0 ) : 0.0774s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9582s for 859290 events => throughput is 8.97E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1062s for 16384 events => throughput is 1.54E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0580s for 16384 events => throughput is 2.83E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0979s for 859290 events => throughput is 8.78E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.6203s for 16384 events => throughput is 6.25E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9150s - [COUNTERS] OVERALL MEs ( 32 ) : 2.6203s for 16384 events => throughput is 6.25E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.6257s for 16384 events => throughput is 6.24E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4567s + [COUNTERS] OVERALL MEs ( 32 ) : 2.6257s for 16384 events => throughput is 6.24E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.7858s - [COUNTERS] Fortran Other ( 0 ) : 0.0926s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0426s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.7889s for 1098402 events => throughput is 6.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.2000s + [COUNTERS] Fortran Other ( 0 ) : 0.0920s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2055s for 1098402 events => throughput is 9.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0795s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0124s for 16384 events => throughput is 1.32E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.55E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0430s for 1098402 events => throughput is 2.56E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.6097s for 16384 events => throughput is 6.28E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.1761s - [COUNTERS] OVERALL MEs ( 32 ) : 2.6097s for 16384 events => throughput is 6.28E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.6087s for 16384 events => throughput is 6.28E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5913s + [COUNTERS] OVERALL MEs ( 32 ) : 2.6087s for 16384 events => throughput is 6.28E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7404s - [COUNTERS] Fortran Other ( 0 ) : 0.0448s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7455s for 378380 events => throughput is 5.08E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.5296s + [COUNTERS] Fortran Other ( 0 ) : 0.0451s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5302s for 378380 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0547s for 16384 events => throughput is 2.99E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0562s for 16384 events => throughput is 2.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0850s for 378380 events => throughput is 4.45E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0845s for 378380 events => throughput is 4.48E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5952s for 16384 events => throughput is 6.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1451s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5952s for 16384 events => throughput is 6.31E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5997s for 16384 events => throughput is 6.30E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9298s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5997s for 16384 events => throughput is 6.30E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/G65/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.3234s - [COUNTERS] Fortran Other ( 0 ) : 0.0731s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3659s for 819579 events => throughput is 6.00E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0145s for 16384 events => throughput is 1.13E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0391s for 819579 events => throughput is 2.10E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 3.8752s + [COUNTERS] Fortran Other ( 0 ) : 0.0727s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9209s for 819579 events => throughput is 8.90E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0813s for 16384 events => throughput is 2.01E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0146s for 16384 events => throughput is 1.13E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0390s for 819579 events => throughput is 2.10E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5983s for 16384 events => throughput is 6.31E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7251s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5983s for 16384 events => throughput is 6.31E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5956s for 16384 events => throughput is 6.31E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2795s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5956s for 16384 events => throughput is 6.31E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 2.2301 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' in 2.0375 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/G55/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2186s - [COUNTERS] Fortran Other ( 0 ) : 0.0443s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6349s for 330261 events => throughput is 5.20E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0270s + [COUNTERS] Fortran Other ( 0 ) : 0.0435s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4450s for 330261 events => throughput is 7.42E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0866s for 81920 events => throughput is 9.46E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0559s for 16384 events => throughput is 2.93E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.88E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0073s for 16384 events => throughput is 2.23E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0198s for 330261 events => throughput is 1.67E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0555s for 16384 events => throughput is 2.95E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0073s for 16384 events => throughput is 2.24E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0196s for 330261 events => throughput is 1.68E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2877s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9309s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2877s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2868s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7402s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2868s for 16384 events => throughput is 1.27E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ddx_epemggg/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 2.8032 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' in 2.2892 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.7921s - [COUNTERS] Fortran Other ( 0 ) : 0.0836s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4473s for 919173 events => throughput is 6.35E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0787s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0846s for 16384 events => throughput is 1.94E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1319s for 919173 events => throughput is 6.97E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.2784s + [COUNTERS] Fortran Other ( 0 ) : 0.0827s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9349s for 919173 events => throughput is 9.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0679s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0837s for 16384 events => throughput is 1.96E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1314s for 919173 events => throughput is 6.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8168s for 16384 events => throughput is 2.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9753s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8168s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8165s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4619s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8165s for 16384 events => throughput is 2.01E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_taptamcuxcx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 18.3149 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' in 15.8788 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9585s - [COUNTERS] Fortran Other ( 0 ) : 0.0321s + [COUNTERS] PROGRAM TOTAL : 1.8747s + [COUNTERS] Fortran Other ( 0 ) : 0.0317s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2775s for 142763 events => throughput is 5.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1932s for 142763 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0655s for 16384 events => throughput is 2.50E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0900s for 142763 events => throughput is 1.59E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 1.2803s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6782s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5944s [COUNTERS] OVERALL MEs ( 32 ) : 1.2803s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7793s - [COUNTERS] Fortran Other ( 0 ) : 0.0972s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8537s for 1119813 events => throughput is 6.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1099s for 16384 events => throughput is 1.49E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1079s for 16384 events => throughput is 1.52E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1708s for 1119813 events => throughput is 6.56E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 3.1670s + [COUNTERS] Fortran Other ( 0 ) : 0.0969s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2427s for 1119813 events => throughput is 9.01E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1093s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1078s for 16384 events => throughput is 1.52E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1705s for 1119813 events => throughput is 6.57E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2806s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4987s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2806s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2809s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8861s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2809s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.9333s - [COUNTERS] Fortran Other ( 0 ) : 0.1094s + [COUNTERS] PROGRAM TOTAL : 3.1940s + [COUNTERS] Fortran Other ( 0 ) : 0.1086s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2228s for 1357398 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0871s for 16384 events => throughput is 1.88E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4825s for 1357398 events => throughput is 9.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0896s for 16384 events => throughput is 1.83E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0172s for 16384 events => throughput is 9.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0556s for 1357398 events => throughput is 2.44E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0172s for 16384 events => throughput is 9.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0553s for 1357398 events => throughput is 2.45E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6514s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2814s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9126s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2814s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5405s - [COUNTERS] Fortran Other ( 0 ) : 0.0515s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7173s for 398526 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0551s for 16384 events => throughput is 2.97E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1146s for 16384 events => throughput is 1.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1652s for 398526 events => throughput is 2.41E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.3039s + [COUNTERS] Fortran Other ( 0 ) : 0.0518s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4794s for 398526 events => throughput is 8.31E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.21E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0563s for 16384 events => throughput is 2.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1141s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1648s for 398526 events => throughput is 2.42E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2860s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2545s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2860s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2861s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0178s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2861s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G53/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.8852s + [COUNTERS] PROGRAM TOTAL : 3.2843s [COUNTERS] Fortran Other ( 0 ) : 0.0905s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9626s for 1103762 events => throughput is 5.62E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0864s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1203s for 16384 events => throughput is 1.36E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3615s for 1103762 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0863s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1204s for 16384 events => throughput is 1.36E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1828s for 1103762 events => throughput is 6.04E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2828s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.6024s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2828s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2834s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0009s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2834s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/G72/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1653s - [COUNTERS] Fortran Other ( 0 ) : 0.0443s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4669s for 272273 events => throughput is 5.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0682s for 49152 events => throughput is 7.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0587s for 16384 events => throughput is 2.79E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0528s for 16384 events => throughput is 3.10E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1096s for 272273 events => throughput is 2.48E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.0031s + [COUNTERS] Fortran Other ( 0 ) : 0.0444s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3055s for 272273 events => throughput is 8.91E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.20E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0586s for 16384 events => throughput is 2.80E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1093s for 272273 events => throughput is 2.49E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8834s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2818s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7213s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2818s for 16384 events => throughput is 1.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gux_epemggux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 2.3662 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' in 2.3003 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/G71/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3540s - [COUNTERS] Fortran Other ( 0 ) : 0.0288s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2218s for 109714 events => throughput is 4.95E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0817s for 49152 events => throughput is 6.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0166s for 16384 events => throughput is 9.86E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.38E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8431s for 16384 events => throughput is 8.89E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5109s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8431s for 16384 events => throughput is 8.89E+03 events/s + [COUNTERS] PROGRAM TOTAL : 2.2903s + [COUNTERS] Fortran Other ( 0 ) : 0.0287s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1564s for 109714 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0821s for 49152 events => throughput is 5.99E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0335s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0167s for 16384 events => throughput is 9.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0250s for 109714 events => throughput is 4.39E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0068s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8439s for 16384 events => throughput is 8.89E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4464s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8439s for 16384 events => throughput is 8.89E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dd_taptamgdd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 2.3958 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' in 1.8841 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/G41/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3843s - [COUNTERS] Fortran Other ( 0 ) : 0.0869s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4825s for 949349 events => throughput is 6.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0786s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0647s for 16384 events => throughput is 2.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1089s for 949349 events => throughput is 8.72E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s + [COUNTERS] PROGRAM TOTAL : 1.8736s + [COUNTERS] Fortran Other ( 0 ) : 0.0861s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9733s for 949349 events => throughput is 9.75E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0791s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0648s for 16384 events => throughput is 2.53E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1081s for 949349 events => throughput is 8.78E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4031s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9812s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4031s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4030s for 16384 events => throughput is 4.07E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4705s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4030s for 16384 events => throughput is 4.07E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemuuxdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 10.7403 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' in 10.2351 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3482s - [COUNTERS] Fortran Other ( 0 ) : 0.0353s + [COUNTERS] PROGRAM TOTAL : 3.2427s + [COUNTERS] Fortran Other ( 0 ) : 0.0354s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3390s for 181152 events => throughput is 5.34E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0773s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2328s for 181152 events => throughput is 7.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0590s for 16384 events => throughput is 2.78E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0905s for 181152 events => throughput is 2.00E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0591s for 16384 events => throughput is 2.77E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0910s for 181152 events => throughput is 1.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5863s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7619s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5863s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6577s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5907s - [COUNTERS] Fortran Other ( 0 ) : 0.0414s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5888s for 293756 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0658s for 16384 events => throughput is 2.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0923s for 293756 events => throughput is 3.18E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 3.4184s + [COUNTERS] Fortran Other ( 0 ) : 0.0418s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4150s for 293756 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0534s for 16384 events => throughput is 3.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0656s for 16384 events => throughput is 2.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0932s for 293756 events => throughput is 3.15E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5889s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0018s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5889s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5893s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8291s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5893s for 16384 events => throughput is 6.33E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.7740s - [COUNTERS] Fortran Other ( 0 ) : 0.0523s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7561s for 405834 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0743s for 16384 events => throughput is 2.21E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1099s for 405834 events => throughput is 3.69E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5763s for 16384 events => throughput is 6.36E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1976s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5763s for 16384 events => throughput is 6.36E+03 events/s + [COUNTERS] PROGRAM TOTAL : 3.5457s + [COUNTERS] Fortran Other ( 0 ) : 0.0525s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5183s for 405834 events => throughput is 7.83E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0744s for 16384 events => throughput is 2.20E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1088s for 405834 events => throughput is 3.73E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5876s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9581s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5876s for 16384 events => throughput is 6.33E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_taptamggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 30.9550 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' in 28.8029 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.5404s - [COUNTERS] Fortran Other ( 0 ) : 0.0776s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4061s for 847188 events => throughput is 6.02E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1031s for 16384 events => throughput is 1.59E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0785s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1234s for 847188 events => throughput is 6.86E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 4.0917s + [COUNTERS] Fortran Other ( 0 ) : 0.0761s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9629s for 847188 events => throughput is 8.80E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1044s for 16384 events => throughput is 1.57E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1225s for 847188 events => throughput is 6.91E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5929s for 16384 events => throughput is 6.32E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9475s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5929s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5881s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5035s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5881s for 16384 events => throughput is 6.33E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G5/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2877s - [COUNTERS] Fortran Other ( 0 ) : 0.0331s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3137s for 167274 events => throughput is 5.33E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1981s + [COUNTERS] Fortran Other ( 0 ) : 0.0332s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2232s for 167274 events => throughput is 7.50E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0809s for 16384 events => throughput is 2.03E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0447s for 16384 events => throughput is 3.67E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0810s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0448s for 16384 events => throughput is 3.65E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0635s for 167274 events => throughput is 2.63E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5935s for 16384 events => throughput is 6.32E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6942s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5935s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5937s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6043s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5937s for 16384 events => throughput is 6.32E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.8987s - [COUNTERS] Fortran Other ( 0 ) : 0.0983s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8878s for 1150245 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] PROGRAM TOTAL : 4.2853s + [COUNTERS] Fortran Other ( 0 ) : 0.0975s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2759s for 1150245 events => throughput is 9.02E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0255s for 16384 events => throughput is 6.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0606s for 1150245 events => throughput is 1.90E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0597s for 1150245 events => throughput is 1.93E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5891s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3095s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5891s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5899s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6954s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5899s for 16384 events => throughput is 6.33E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5885s + [COUNTERS] PROGRAM TOTAL : 3.3812s [COUNTERS] Fortran Other ( 0 ) : 0.0476s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6610s for 355348 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0536s for 16384 events => throughput is 3.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4533s for 355348 events => throughput is 7.84E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0538s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0296s for 16384 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0481s for 355348 events => throughput is 7.39E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 355348 events => throughput is 7.44E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 2.5900s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9985s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7911s [COUNTERS] OVERALL MEs ( 32 ) : 2.5900s for 16384 events => throughput is 6.33E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.5651s - [COUNTERS] Fortran Other ( 0 ) : 0.0790s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4200s for 864266 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1070s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1286s for 864266 events => throughput is 6.72E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 4.1087s + [COUNTERS] Fortran Other ( 0 ) : 0.0788s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9652s for 864266 events => throughput is 8.95E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1057s for 16384 events => throughput is 1.55E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0786s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1278s for 864266 events => throughput is 6.76E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5930s for 16384 events => throughput is 6.32E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9721s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5930s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5931s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5156s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5931s for 16384 events => throughput is 6.32E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G39/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5420s - [COUNTERS] Fortran Other ( 0 ) : 0.0399s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5661s for 285525 events => throughput is 5.04E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0766s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3834s + [COUNTERS] Fortran Other ( 0 ) : 0.0401s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0429s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4053s for 285525 events => throughput is 7.04E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0765s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0535s for 16384 events => throughput is 3.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0586s for 16384 events => throughput is 2.80E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0804s for 285525 events => throughput is 3.55E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0584s for 16384 events => throughput is 2.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0803s for 285525 events => throughput is 3.56E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5841s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9579s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5841s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5852s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7982s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5852s for 16384 events => throughput is 6.34E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2816s - [COUNTERS] Fortran Other ( 0 ) : 0.0366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3398s for 189666 events => throughput is 5.58E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.21E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0820s for 16384 events => throughput is 2.00E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0298s for 16384 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0535s for 189666 events => throughput is 3.55E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.1727s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2293s for 189666 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0299s for 16384 events => throughput is 5.47E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0534s for 189666 events => throughput is 3.55E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5891s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6925s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5891s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5904s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5823s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5904s for 16384 events => throughput is 6.32E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1813s - [COUNTERS] Fortran Other ( 0 ) : 0.0306s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2488s for 124553 events => throughput is 5.01E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1140s + [COUNTERS] Fortran Other ( 0 ) : 0.0304s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1766s for 124553 events => throughput is 7.05E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.87E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0589s for 124553 events => throughput is 2.12E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0423s for 16384 events => throughput is 3.88E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0588s for 124553 events => throughput is 2.12E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5876s for 16384 events => throughput is 6.33E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5937s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5876s for 16384 events => throughput is 6.33E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5920s for 16384 events => throughput is 6.32E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5220s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5920s for 16384 events => throughput is 6.32E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 4.6985 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' in 4.3063 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G48/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3309s - [COUNTERS] Fortran Other ( 0 ) : 0.0443s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0429s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5753s for 318589 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.24E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.1379s + [COUNTERS] Fortran Other ( 0 ) : 0.0438s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3853s for 318589 events => throughput is 8.27E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0520s for 16384 events => throughput is 3.15E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0880s for 16384 events => throughput is 1.86E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1292s for 318589 events => throughput is 2.47E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1289s for 318589 events => throughput is 2.47E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2787s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0521s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2787s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2785s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8594s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2785s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3483s - [COUNTERS] Fortran Other ( 0 ) : 0.0429s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6628s for 343552 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0522s for 16384 events => throughput is 3.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0604s for 16384 events => throughput is 2.71E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.1492s + [COUNTERS] Fortran Other ( 0 ) : 0.0443s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4625s for 343552 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.32E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0606s for 16384 events => throughput is 2.70E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0878s for 343552 events => throughput is 3.91E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0663s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2819s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2811s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8681s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2811s for 16384 events => throughput is 1.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 15.5195 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' in 13.9745 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1330s - [COUNTERS] Fortran Other ( 0 ) : 0.0360s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4005s for 223142 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0779s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1096s for 223142 events => throughput is 2.04E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.0045s + [COUNTERS] Fortran Other ( 0 ) : 0.0358s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2723s for 223142 events => throughput is 8.20E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0685s for 16384 events => throughput is 2.39E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1095s for 223142 events => throughput is 2.04E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2795s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8535s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2795s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2789s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7256s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2789s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3164s - [COUNTERS] Fortran Other ( 0 ) : 0.0417s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6240s for 323723 events => throughput is 5.19E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0787s for 49152 events => throughput is 6.25E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.1279s + [COUNTERS] Fortran Other ( 0 ) : 0.0425s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4359s for 323723 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0790s for 49152 events => throughput is 6.22E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.14E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0599s for 16384 events => throughput is 2.73E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0863s for 323723 events => throughput is 3.75E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0864s for 323723 events => throughput is 3.75E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2898s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0265s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2898s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2887s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8392s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2887s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G35/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1945s - [COUNTERS] Fortran Other ( 0 ) : 0.0371s + [COUNTERS] PROGRAM TOTAL : 2.0591s + [COUNTERS] Fortran Other ( 0 ) : 0.0376s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4377s for 243889 events => throughput is 5.57E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2982s for 243889 events => throughput is 8.18E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.05E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0748s for 16384 events => throughput is 2.19E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1105s for 243889 events => throughput is 2.21E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0737s for 16384 events => throughput is 2.22E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1087s for 243889 events => throughput is 2.24E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2936s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9008s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2936s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2999s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7593s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2999s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G36/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2834s - [COUNTERS] Fortran Other ( 0 ) : 0.0416s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6167s for 320856 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0987s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4327s for 320856 events => throughput is 7.41E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0786s for 49152 events => throughput is 6.25E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0523s for 16384 events => throughput is 3.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0496s for 16384 events => throughput is 3.30E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0729s for 320856 events => throughput is 4.40E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0494s for 16384 events => throughput is 3.32E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0726s for 320856 events => throughput is 4.42E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2894s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9941s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2894s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2896s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8090s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2896s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G34/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.0045s - [COUNTERS] Fortran Other ( 0 ) : 0.0994s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.2227s for 1259120 events => throughput is 5.66E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 49152 events => throughput is 6.32E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0867s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0502s for 16384 events => throughput is 3.26E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0964s for 1259120 events => throughput is 1.31E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 3.3337s + [COUNTERS] Fortran Other ( 0 ) : 0.0984s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5536s for 1259120 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0864s for 16384 events => throughput is 1.90E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0351s for 16384 events => throughput is 4.67E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0503s for 16384 events => throughput is 3.26E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0961s for 1259120 events => throughput is 1.31E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2881s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.7164s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2881s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2870s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0467s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2870s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.5350s - [COUNTERS] Fortran Other ( 0 ) : 0.0502s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7255s for 403861 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 49152 events => throughput is 6.27E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0527s for 16384 events => throughput is 3.11E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.2995s + [COUNTERS] Fortran Other ( 0 ) : 0.0507s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4867s for 403861 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 49152 events => throughput is 6.28E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.08E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1070s for 16384 events => throughput is 1.53E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1511s for 403861 events => throughput is 2.67E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1521s for 403861 events => throughput is 2.66E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2867s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2483s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2867s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0110s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2885s for 16384 events => throughput is 1.27E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_epemgddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 2.4770 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' in 2.1539 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2645s - [COUNTERS] Fortran Other ( 0 ) : 0.0415s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5541s for 285337 events => throughput is 5.15E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0838s for 81920 events => throughput is 9.78E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0410s for 16384 events => throughput is 3.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0259s for 16384 events => throughput is 6.32E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0412s for 285337 events => throughput is 6.92E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0947s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3841s for 285337 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0832s for 81920 events => throughput is 9.85E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0406s for 16384 events => throughput is 4.03E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0260s for 16384 events => throughput is 6.31E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0411s for 285337 events => throughput is 6.95E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0052s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3962s for 16384 events => throughput is 4.13E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8682s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3962s for 16384 events => throughput is 4.13E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3976s for 16384 events => throughput is 4.12E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6971s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3976s for 16384 events => throughput is 4.12E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/G46/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1921s - [COUNTERS] Fortran Other ( 0 ) : 0.0410s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4722s for 258650 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.14E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0424s for 16384 events => throughput is 3.86E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0378s for 16384 events => throughput is 4.33E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0542s for 258650 events => throughput is 4.77E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.0393s + [COUNTERS] Fortran Other ( 0 ) : 0.0414s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3188s for 258650 events => throughput is 8.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0427s for 16384 events => throughput is 3.84E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0378s for 16384 events => throughput is 4.34E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 258650 events => throughput is 4.81E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3948s for 16384 events => throughput is 4.15E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7973s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3948s for 16384 events => throughput is 4.15E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3947s for 16384 events => throughput is 4.15E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6446s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3947s for 16384 events => throughput is 4.15E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemsdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 2.8864 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' in 2.4026 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G25/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.8030s - [COUNTERS] Fortran Other ( 0 ) : 0.0680s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.0992s for 669977 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0630s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0030s for 16384 events => throughput is 5.42E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0220s for 669977 events => throughput is 3.04E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0052s + [COUNTERS] PROGRAM TOTAL : 1.4433s + [COUNTERS] Fortran Other ( 0 ) : 0.0681s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.7382s for 669977 events => throughput is 9.08E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0691s for 49152 events => throughput is 7.12E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0636s for 16384 events => throughput is 2.57E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0031s for 16384 events => throughput is 5.34E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0216s for 669977 events => throughput is 3.10E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.3986s for 16384 events => throughput is 4.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4044s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0447s [COUNTERS] OVERALL MEs ( 32 ) : 0.3986s for 16384 events => throughput is 4.11E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0636s - [COUNTERS] Fortran Other ( 0 ) : 0.0351s + [COUNTERS] PROGRAM TOTAL : 0.9410s + [COUNTERS] Fortran Other ( 0 ) : 0.0343s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3709s for 205420 events => throughput is 5.54E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0685s for 49152 events => throughput is 7.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0690s for 16384 events => throughput is 2.37E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2507s for 205420 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0677s for 16384 events => throughput is 2.42E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0151s for 16384 events => throughput is 1.09E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0258s for 205420 events => throughput is 7.95E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0150s for 16384 events => throughput is 1.09E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0257s for 205420 events => throughput is 7.99E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3983s for 16384 events => throughput is 4.11E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6653s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3983s for 16384 events => throughput is 4.11E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3979s for 16384 events => throughput is 4.12E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5430s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3979s for 16384 events => throughput is 4.12E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dxsx_epemgdxsx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 14.7329 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' in 13.7838 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1353s - [COUNTERS] Fortran Other ( 0 ) : 0.0365s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3919s for 218285 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0773s for 81920 events => throughput is 1.06E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0778s for 16384 events => throughput is 2.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.0097s + [COUNTERS] Fortran Other ( 0 ) : 0.0359s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2643s for 218285 events => throughput is 8.26E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0781s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0721s for 16384 events => throughput is 2.27E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1166s for 218285 events => throughput is 1.87E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1167s for 218285 events => throughput is 1.87E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2802s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8550s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2802s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2815s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7282s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2815s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1994s - [COUNTERS] Fortran Other ( 0 ) : 0.0440s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0427s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5718s for 318651 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0783s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0521s for 16384 events => throughput is 3.15E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0359s for 16384 events => throughput is 4.56E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0536s for 318651 events => throughput is 5.94E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] PROGRAM TOTAL : 2.0289s + [COUNTERS] Fortran Other ( 0 ) : 0.0443s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3824s for 318651 events => throughput is 8.33E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0549s for 16384 events => throughput is 2.99E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0360s for 16384 events => throughput is 4.55E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0537s for 318651 events => throughput is 5.94E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2798s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9196s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2798s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2973s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7316s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2973s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9725s - [COUNTERS] Fortran Other ( 0 ) : 0.0326s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2982s for 164085 events => throughput is 5.50E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0771s for 16384 events => throughput is 2.13E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0515s for 16384 events => throughput is 3.18E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0735s for 164085 events => throughput is 2.23E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.8818s + [COUNTERS] Fortran Other ( 0 ) : 0.0328s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0432s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2046s for 164085 events => throughput is 8.02E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0770s for 16384 events => throughput is 2.13E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0516s for 16384 events => throughput is 3.18E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0727s for 164085 events => throughput is 2.26E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2787s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6938s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2787s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2806s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6013s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2806s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9681s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s + [COUNTERS] PROGRAM TOTAL : 1.8643s + [COUNTERS] Fortran Other ( 0 ) : 0.0340s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3435s for 177884 events => throughput is 5.18E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0778s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2393s for 177884 events => throughput is 7.43E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0409s for 16384 events => throughput is 4.00E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0572s for 177884 events => throughput is 3.11E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0409s for 16384 events => throughput is 4.01E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0571s for 177884 events => throughput is 3.11E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2782s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6899s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2782s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2786s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5857s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2786s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9299s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3769s for 206659 events => throughput is 5.48E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0096s for 16384 events => throughput is 1.70E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0191s for 206659 events => throughput is 1.08E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.8036s + [COUNTERS] Fortran Other ( 0 ) : 0.0359s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2536s for 206659 events => throughput is 8.15E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0543s for 16384 events => throughput is 3.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0095s for 16384 events => throughput is 1.73E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0189s for 206659 events => throughput is 1.10E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2818s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6481s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2818s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2795s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5241s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2795s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G70/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9744s - [COUNTERS] Fortran Other ( 0 ) : 0.0362s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3340s for 195643 events => throughput is 5.86E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0693s for 49152 events => throughput is 7.09E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0798s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0324s for 16384 events => throughput is 5.06E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0601s for 195643 events => throughput is 3.25E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 1.8593s + [COUNTERS] Fortran Other ( 0 ) : 0.0363s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2192s for 195643 events => throughput is 8.92E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0694s for 49152 events => throughput is 7.08E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0324s for 16384 events => throughput is 5.05E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0601s for 195643 events => throughput is 3.26E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2796s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6947s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2796s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2797s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5796s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2797s for 16384 events => throughput is 1.28E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/G80/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4922s - [COUNTERS] Fortran Other ( 0 ) : 0.0480s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6615s for 370750 events => throughput is 5.60E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1139s for 16384 events => throughput is 1.44E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1770s for 370750 events => throughput is 2.09E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 2.2765s + [COUNTERS] Fortran Other ( 0 ) : 0.0491s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4455s for 370750 events => throughput is 8.32E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0776s for 81920 events => throughput is 1.06E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.1140s for 16384 events => throughput is 1.44E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1771s for 370750 events => throughput is 2.09E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2784s for 16384 events => throughput is 1.28E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.2138s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2784s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2777s for 16384 events => throughput is 1.28E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9988s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2777s for 16384 events => throughput is 1.28E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gdx_epemggdx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 2.4051 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' in 1.8695 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/G42/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.3941s - [COUNTERS] Fortran Other ( 0 ) : 0.0903s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.5179s for 974583 events => throughput is 6.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0681s for 49152 events => throughput is 7.22E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0788s for 16384 events => throughput is 2.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0582s for 16384 events => throughput is 2.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0940s for 974583 events => throughput is 1.04E+07 events/s + [COUNTERS] PROGRAM TOTAL : 1.8585s + [COUNTERS] Fortran Other ( 0 ) : 0.0889s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9827s for 974583 events => throughput is 9.92E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0589s for 16384 events => throughput is 2.78E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0937s for 974583 events => throughput is 1.04E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4054s for 16384 events => throughput is 4.04E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.9886s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4054s for 16384 events => throughput is 4.04E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4053s for 16384 events => throughput is 4.04E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4532s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4053s for 16384 events => throughput is 4.04E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 38.6530 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' in 34.0149 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G1/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.1690s - [COUNTERS] Fortran Other ( 0 ) : 0.0776s + [COUNTERS] PROGRAM TOTAL : 2.7093s + [COUNTERS] Fortran Other ( 0 ) : 0.0770s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4216s for 850849 events => throughput is 5.99E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9628s for 850849 events => throughput is 8.84E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1095s for 16384 events => throughput is 1.50E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0368s for 16384 events => throughput is 4.45E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0676s for 850849 events => throughput is 1.26E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2973s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8717s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2973s for 16384 events => throughput is 1.26E+04 events/s -/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log - [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0877s - [COUNTERS] Fortran Other ( 0 ) : 0.0724s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0424s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3879s for 778343 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0887s for 16384 events => throughput is 1.85E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0286s for 16384 events => throughput is 5.74E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0549s for 778343 events => throughput is 1.42E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1088s for 16384 events => throughput is 1.51E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0369s for 16384 events => throughput is 4.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0673s for 850849 events => throughput is 1.26E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2950s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7927s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2950s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2976s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.4117s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2976s for 16384 events => throughput is 1.26E+04 events/s +/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G3/GridRun_21_app.log + [COUNTERS] *** USING RDTSC-BASED TIMERS *** + [COUNTERS] PROGRAM TOTAL : 2.6561s + [COUNTERS] Fortran Other ( 0 ) : 0.0712s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9618s for 778343 events => throughput is 8.09E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0755s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0884s for 16384 events => throughput is 1.85E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0285s for 16384 events => throughput is 5.75E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0544s for 778343 events => throughput is 1.43E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2938s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.3623s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2938s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G9/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6505s - [COUNTERS] Fortran Other ( 0 ) : 0.1011s + [COUNTERS] PROGRAM TOTAL : 3.0022s + [COUNTERS] Fortran Other ( 0 ) : 0.1000s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.9547s for 1190413 events => throughput is 6.09E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0758s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0860s for 16384 events => throughput is 1.90E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0106s for 16384 events => throughput is 1.54E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0443s for 1190413 events => throughput is 2.69E+07 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.3074s for 1190413 events => throughput is 9.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0857s for 16384 events => throughput is 1.91E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0107s for 16384 events => throughput is 1.53E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0441s for 1190413 events => throughput is 2.70E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2955s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3549s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2955s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2960s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.7062s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2960s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.2241s + [COUNTERS] PROGRAM TOTAL : 2.0397s [COUNTERS] Fortran Other ( 0 ) : 0.0451s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.5649s for 314106 events => throughput is 5.56E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3800s for 314106 events => throughput is 8.27E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0545s for 16384 events => throughput is 3.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0548s for 16384 events => throughput is 2.99E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0403s for 16384 events => throughput is 4.07E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0620s for 314106 events => throughput is 5.07E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0402s for 16384 events => throughput is 4.08E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0620s for 314106 events => throughput is 5.06E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2982s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9258s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2982s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2987s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7409s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2987s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G13/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3085s - [COUNTERS] Fortran Other ( 0 ) : 0.0810s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.4547s for 882930 events => throughput is 6.07E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0768s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1105s for 16384 events => throughput is 1.48E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0782s for 16384 events => throughput is 2.10E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1285s for 882930 events => throughput is 6.87E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.8328s + [COUNTERS] Fortran Other ( 0 ) : 0.0826s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.9809s for 882930 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1095s for 16384 events => throughput is 1.50E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0781s for 16384 events => throughput is 2.10E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1277s for 882930 events => throughput is 6.91E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2953s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.0131s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2953s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0005s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2945s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.5383s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2945s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0697s - [COUNTERS] Fortran Other ( 0 ) : 0.0347s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3448s for 187611 events => throughput is 5.44E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0801s for 16384 events => throughput is 2.05E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0609s for 16384 events => throughput is 2.69E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0949s for 187611 events => throughput is 1.98E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.9545s + [COUNTERS] Fortran Other ( 0 ) : 0.0344s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2283s for 187611 events => throughput is 8.22E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0811s for 16384 events => throughput is 2.02E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0606s for 16384 events => throughput is 2.70E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0945s for 187611 events => throughput is 1.98E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2959s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7739s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2959s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2968s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6577s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2968s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G33/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 4.6755s - [COUNTERS] Fortran Other ( 0 ) : 0.1366s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 2.7807s for 1696178 events => throughput is 6.10E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0683s for 49152 events => throughput is 7.20E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0874s for 16384 events => throughput is 1.87E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0832s for 16384 events => throughput is 1.97E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1432s for 1696178 events => throughput is 1.18E+07 events/s + [COUNTERS] PROGRAM TOTAL : 3.7539s + [COUNTERS] Fortran Other ( 0 ) : 0.1352s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8609s for 1696178 events => throughput is 9.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0684s for 49152 events => throughput is 7.19E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0875s for 16384 events => throughput is 1.87E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0826s for 16384 events => throughput is 1.98E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1428s for 1696178 events => throughput is 1.19E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2935s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 3.3820s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2935s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2944s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.4595s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2944s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G6/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.9386s - [COUNTERS] Fortran Other ( 0 ) : 0.0311s + [COUNTERS] PROGRAM TOTAL : 1.8564s + [COUNTERS] Fortran Other ( 0 ) : 0.0317s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2690s for 138227 events => throughput is 5.14E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1880s for 138227 events => throughput is 7.35E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0760s for 81920 events => throughput is 1.08E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0556s for 16384 events => throughput is 2.95E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0540s for 16384 events => throughput is 3.03E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0751s for 138227 events => throughput is 1.84E+06 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0539s for 16384 events => throughput is 3.04E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0750s for 138227 events => throughput is 1.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2952s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6434s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2952s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2938s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5626s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2938s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0387s - [COUNTERS] Fortran Other ( 0 ) : 0.0393s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3680s for 215899 events => throughput is 5.87E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0302s for 16384 events => throughput is 5.43E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0666s for 215899 events => throughput is 3.24E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2962s for 16384 events => throughput is 1.26E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7425s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2962s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] PROGRAM TOTAL : 1.9124s + [COUNTERS] Fortran Other ( 0 ) : 0.0395s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2399s for 215899 events => throughput is 9.00E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0803s for 16384 events => throughput is 2.04E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0300s for 16384 events => throughput is 5.45E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0662s for 215899 events => throughput is 3.26E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2976s for 16384 events => throughput is 1.26E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6147s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2976s for 16384 events => throughput is 1.26E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0917s - [COUNTERS] Fortran Other ( 0 ) : 0.0389s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4911s for 254421 events => throughput is 5.18E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.9516s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3478s for 254421 events => throughput is 7.31E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0757s for 81920 events => throughput is 1.08E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0544s for 16384 events => throughput is 3.01E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0560s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0208s for 16384 events => throughput is 7.89E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0342s for 254421 events => throughput is 7.45E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2944s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7973s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2944s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2950s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6566s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2950s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6612s - [COUNTERS] Fortran Other ( 0 ) : 0.0872s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8248s for 1024423 events => throughput is 5.61E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0762s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0865s for 16384 events => throughput is 1.89E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0784s for 16384 events => throughput is 2.09E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1336s for 1024423 events => throughput is 7.67E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 3.0953s + [COUNTERS] Fortran Other ( 0 ) : 0.0871s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2602s for 1024423 events => throughput is 8.13E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0867s for 16384 events => throughput is 1.89E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0783s for 16384 events => throughput is 2.09E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1326s for 1024423 events => throughput is 7.72E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2910s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.3702s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2910s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2913s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.8040s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2913s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.0034s - [COUNTERS] Fortran Other ( 0 ) : 0.0372s + [COUNTERS] PROGRAM TOTAL : 1.8893s + [COUNTERS] Fortran Other ( 0 ) : 0.0368s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3335s for 193396 events => throughput is 5.80E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0680s for 49152 events => throughput is 7.23E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0952s for 16384 events => throughput is 1.72E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.84E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2200s for 193396 events => throughput is 8.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0678s for 49152 events => throughput is 7.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0963s for 16384 events => throughput is 1.70E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.84E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0315s for 16384 events => throughput is 5.20E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0606s for 193396 events => throughput is 3.19E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0600s for 193396 events => throughput is 3.22E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2951s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7083s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2951s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2945s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5948s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2945s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G79/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4484s - [COUNTERS] Fortran Other ( 0 ) : 0.0488s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6502s for 362054 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0763s for 81920 events => throughput is 1.07E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0549s for 16384 events => throughput is 2.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0960s for 16384 events => throughput is 1.71E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1453s for 362054 events => throughput is 2.49E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] PROGRAM TOTAL : 2.2339s + [COUNTERS] Fortran Other ( 0 ) : 0.0482s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4361s for 362054 events => throughput is 8.30E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0764s for 81920 events => throughput is 1.07E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0552s for 16384 events => throughput is 2.97E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0961s for 16384 events => throughput is 1.71E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.1458s for 362054 events => throughput is 2.48E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2943s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.1540s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2943s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2935s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.9404s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2935s for 16384 events => throughput is 1.27E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/G76/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.1691s - [COUNTERS] Fortran Other ( 0 ) : 0.0454s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4558s for 265638 events => throughput is 5.83E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0759s for 81920 events => throughput is 1.08E+06 events/s + [COUNTERS] PROGRAM TOTAL : 2.0114s + [COUNTERS] Fortran Other ( 0 ) : 0.0450s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3000s for 265638 events => throughput is 8.85E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0761s for 81920 events => throughput is 1.08E+06 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0767s for 16384 events => throughput is 2.14E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0500s for 16384 events => throughput is 3.28E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0888s for 265638 events => throughput is 2.99E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.2934s for 16384 events => throughput is 1.27E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8757s - [COUNTERS] OVERALL MEs ( 32 ) : 1.2934s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.2920s for 16384 events => throughput is 1.27E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7194s + [COUNTERS] OVERALL MEs ( 32 ) : 1.2920s for 16384 events => throughput is 1.27E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_epemggu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.6327 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' in 1.4781 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.6214s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4903s for 259134 events => throughput is 5.29E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0429s for 16384 events => throughput is 3.82E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0318s for 16384 events => throughput is 5.16E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0478s for 259134 events => throughput is 5.42E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s + [COUNTERS] PROGRAM TOTAL : 1.4676s + [COUNTERS] Fortran Other ( 0 ) : 0.0408s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3377s for 259134 events => throughput is 7.67E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0677s for 49152 events => throughput is 7.26E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.82E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0317s for 16384 events => throughput is 5.17E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0477s for 259134 events => throughput is 5.43E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8169s for 16384 events => throughput is 2.01E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8044s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8169s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8177s for 16384 events => throughput is 2.00E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6499s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8177s for 16384 events => throughput is 2.00E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gu_taptamuddx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 4.1747 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' in 3.7333 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0196s - [COUNTERS] Fortran Other ( 0 ) : 0.0343s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3377s for 187490 events => throughput is 5.55E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0707s for 49152 events => throughput is 6.95E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0677s for 16384 events => throughput is 2.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9111s + [COUNTERS] Fortran Other ( 0 ) : 0.0346s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2298s for 187490 events => throughput is 8.16E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0675s for 16384 events => throughput is 2.43E+05 events/s INFO: The following Floating Point Exceptions have been reported: FE_UNDERFLOW - [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0077s for 16384 events => throughput is 2.13E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0167s for 187490 events => throughput is 1.12E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4040s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6156s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4040s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0077s for 16384 events => throughput is 2.12E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0166s for 187490 events => throughput is 1.13E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0052s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0003s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4036s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5075s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4036s for 16384 events => throughput is 4.06E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1028s - [COUNTERS] Fortran Other ( 0 ) : 0.0407s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4132s for 229909 events => throughput is 5.56E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0703s for 49152 events => throughput is 6.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0442s for 16384 events => throughput is 3.71E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0179s for 16384 events => throughput is 9.15E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9647s + [COUNTERS] Fortran Other ( 0 ) : 0.0400s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2774s for 229909 events => throughput is 8.29E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0439s for 16384 events => throughput is 3.73E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0178s for 16384 events => throughput is 9.22E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0303s for 229909 events => throughput is 7.59E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4045s for 16384 events => throughput is 4.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6983s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4045s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4044s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5602s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4044s for 16384 events => throughput is 4.05E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G45/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0189s - [COUNTERS] Fortran Other ( 0 ) : 0.0336s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0423s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3236s for 170163 events => throughput is 5.26E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0457s for 16384 events => throughput is 3.58E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.73E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0237s for 16384 events => throughput is 6.91E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0354s for 170163 events => throughput is 4.81E+06 events/s + [COUNTERS] PROGRAM TOTAL : 0.9205s + [COUNTERS] Fortran Other ( 0 ) : 0.0333s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0420s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2252s for 170163 events => throughput is 7.55E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0701s for 49152 events => throughput is 7.01E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0453s for 16384 events => throughput is 3.62E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0241s for 16384 events => throughput is 6.80E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0363s for 170163 events => throughput is 4.69E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4044s for 16384 events => throughput is 4.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6145s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5161s [COUNTERS] OVERALL MEs ( 32 ) : 0.4044s for 16384 events => throughput is 4.05E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/G38/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9967s + [COUNTERS] PROGRAM TOTAL : 0.9019s [COUNTERS] Fortran Other ( 0 ) : 0.0323s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2869s for 155440 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.99E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0696s for 16384 events => throughput is 2.35E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0204s for 16384 events => throughput is 8.02E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0311s for 155440 events => throughput is 4.99E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1930s for 155440 events => throughput is 8.05E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0695s for 16384 events => throughput is 2.36E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 8.00E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0310s for 155440 events => throughput is 5.01E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4046s for 16384 events => throughput is 4.05E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5921s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4046s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4043s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4976s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4043s for 16384 events => throughput is 4.05E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_epemgudx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 10.3180 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' in 9.7947 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G19/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4845s - [COUNTERS] Fortran Other ( 0 ) : 0.0374s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3595s for 193303 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0802s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0532s for 16384 events => throughput is 3.08E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0045s for 16384 events => throughput is 3.63E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0127s for 193303 events => throughput is 1.52E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s + [COUNTERS] PROGRAM TOTAL : 2.3746s + [COUNTERS] Fortran Other ( 0 ) : 0.0367s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2483s for 193303 events => throughput is 7.78E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0801s for 49152 events => throughput is 6.13E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0530s for 16384 events => throughput is 3.09E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0045s for 16384 events => throughput is 3.65E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0128s for 193303 events => throughput is 1.51E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8545s for 16384 events => throughput is 8.83E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6300s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8545s for 16384 events => throughput is 8.83E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8566s for 16384 events => throughput is 8.82E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5180s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8566s for 16384 events => throughput is 8.82E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G21/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.9008s - [COUNTERS] Fortran Other ( 0 ) : 0.0534s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6768s for 430212 events => throughput is 6.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.18E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1042s for 16384 events => throughput is 1.57E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0345s for 16384 events => throughput is 4.75E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0173s for 16384 events => throughput is 9.49E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0333s for 430212 events => throughput is 1.29E+07 events/s + [COUNTERS] PROGRAM TOTAL : 2.6698s + [COUNTERS] Fortran Other ( 0 ) : 0.0532s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4451s for 430212 events => throughput is 9.67E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0796s for 49152 events => throughput is 6.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.1028s for 16384 events => throughput is 1.59E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0172s for 16384 events => throughput is 9.50E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0332s for 430212 events => throughput is 1.30E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8535s for 16384 events => throughput is 8.84E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0473s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8535s for 16384 events => throughput is 8.84E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8555s for 16384 events => throughput is 8.83E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8142s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8555s for 16384 events => throughput is 8.83E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4511s - [COUNTERS] Fortran Other ( 0 ) : 0.0318s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2888s for 154293 events => throughput is 5.34E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0804s for 49152 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0792s for 16384 events => throughput is 2.07E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0099s for 16384 events => throughput is 1.66E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.55E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8603s for 16384 events => throughput is 8.81E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5908s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8603s for 16384 events => throughput is 8.81E+03 events/s + [COUNTERS] PROGRAM TOTAL : 2.3625s + [COUNTERS] Fortran Other ( 0 ) : 0.0319s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0411s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1980s for 154293 events => throughput is 7.79E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0806s for 49152 events => throughput is 6.10E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0794s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.77E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0099s for 16384 events => throughput is 1.65E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0180s for 154293 events => throughput is 8.57E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0068s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8622s for 16384 events => throughput is 8.80E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5003s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8622s for 16384 events => throughput is 8.80E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/G52/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 2.4448s - [COUNTERS] Fortran Other ( 0 ) : 0.0318s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3196s for 159370 events => throughput is 4.99E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0813s for 49152 events => throughput is 6.05E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0529s for 16384 events => throughput is 3.10E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.3526s + [COUNTERS] Fortran Other ( 0 ) : 0.0317s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2259s for 159370 events => throughput is 7.06E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0794s for 49152 events => throughput is 6.19E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0533s for 16384 events => throughput is 3.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.95E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0130s for 159370 events => throughput is 1.22E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0054s for 16384 events => throughput is 3.04E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0129s for 159370 events => throughput is 1.23E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 1.8579s for 16384 events => throughput is 8.82E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5868s - [COUNTERS] OVERALL MEs ( 32 ) : 1.8579s for 16384 events => throughput is 8.82E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 1.8617s for 16384 events => throughput is 8.80E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4909s + [COUNTERS] OVERALL MEs ( 32 ) : 1.8617s for 16384 events => throughput is 8.80E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_taptamguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 3.3482 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' in 2.9394 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G27/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0963s - [COUNTERS] Fortran Other ( 0 ) : 0.0358s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3845s for 212440 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9718s + [COUNTERS] Fortran Other ( 0 ) : 0.0361s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2595s for 212440 events => throughput is 8.19E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0706s for 49152 events => throughput is 6.96E+05 events/s [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0683s for 16384 events => throughput is 2.40E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.73E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0201s for 16384 events => throughput is 8.14E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0323s for 212440 events => throughput is 6.58E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.76E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0202s for 16384 events => throughput is 8.10E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 212440 events => throughput is 6.59E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4032s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6931s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4032s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4035s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5683s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4035s for 16384 events => throughput is 4.06E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1303s - [COUNTERS] Fortran Other ( 0 ) : 0.0413s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4532s for 250568 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0704s for 49152 events => throughput is 6.98E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0435s for 16384 events => throughput is 3.77E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0346s for 16384 events => throughput is 4.74E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9813s + [COUNTERS] Fortran Other ( 0 ) : 0.0412s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3048s for 250568 events => throughput is 8.22E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0707s for 49152 events => throughput is 6.95E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.78E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.78E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0125s for 16384 events => throughput is 1.31E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0241s for 250568 events => throughput is 1.04E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4034s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7269s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4034s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4036s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5776s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4036s for 16384 events => throughput is 4.06E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0935s - [COUNTERS] Fortran Other ( 0 ) : 0.0368s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4114s for 227751 events => throughput is 5.54E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.9597s + [COUNTERS] Fortran Other ( 0 ) : 0.0366s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2787s for 227751 events => throughput is 8.17E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0677s for 16384 events => throughput is 2.42E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0675s for 16384 events => throughput is 2.43E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0060s for 16384 events => throughput is 2.72E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0164s for 227751 events => throughput is 1.39E+07 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0155s for 227751 events => throughput is 1.47E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s - [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0001s + [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.4031s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6904s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5566s [COUNTERS] OVERALL MEs ( 32 ) : 0.4031s for 16384 events => throughput is 4.06E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dux_epemgdux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 1.0531 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' in 0.9420 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0426s + [COUNTERS] PROGRAM TOTAL : 0.9319s [COUNTERS] Fortran Other ( 0 ) : 0.0331s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3587s for 184243 events => throughput is 5.14E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0689s for 49152 events => throughput is 7.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.73E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0348s for 16384 events => throughput is 4.71E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0248s for 16384 events => throughput is 6.60E+05 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2494s for 184243 events => throughput is 7.39E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0687s for 49152 events => throughput is 7.15E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0443s for 16384 events => throughput is 3.70E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0249s for 16384 events => throughput is 6.59E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0380s for 184243 events => throughput is 4.85E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0052s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.3935s for 16384 events => throughput is 4.16E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6492s - [COUNTERS] OVERALL MEs ( 32 ) : 0.3935s for 16384 events => throughput is 4.16E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.3929s for 16384 events => throughput is 4.17E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5390s + [COUNTERS] OVERALL MEs ( 32 ) : 0.3929s for 16384 events => throughput is 4.17E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ds_epemgds/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 3.0593 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' in 2.4405 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/G14/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.0479s - [COUNTERS] Fortran Other ( 0 ) : 0.0980s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.8723s for 1143085 events => throughput is 6.11E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0688s for 49152 events => throughput is 7.15E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0566s for 16384 events => throughput is 2.90E+05 events/s + [COUNTERS] PROGRAM TOTAL : 2.4297s + [COUNTERS] Fortran Other ( 0 ) : 0.0966s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 1.2551s for 1143085 events => throughput is 9.11E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0686s for 49152 events => throughput is 7.17E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0566s for 16384 events => throughput is 2.89E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0108s for 16384 events => throughput is 1.51E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0433s for 1143085 events => throughput is 2.64E+07 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0110s for 16384 events => throughput is 1.49E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0434s for 1143085 events => throughput is 2.63E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8172s for 16384 events => throughput is 2.00E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 2.2307s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8172s for 16384 events => throughput is 2.00E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8169s for 16384 events => throughput is 2.01E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.6127s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8169s for 16384 events => throughput is 2.01E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ucx_taptamgucx/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 10.2709 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' in 9.8636 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G11/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.5931s - [COUNTERS] Fortran Other ( 0 ) : 0.0458s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6183s for 332018 events => throughput is 5.37E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0782s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0526s for 16384 events => throughput is 3.11E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0532s for 16384 events => throughput is 3.08E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.3992s + [COUNTERS] Fortran Other ( 0 ) : 0.0462s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4245s for 332018 events => throughput is 7.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0779s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0525s for 16384 events => throughput is 3.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0531s for 16384 events => throughput is 3.09E+05 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0788s for 332018 events => throughput is 4.21E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5835s for 16384 events => throughput is 6.34E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0096s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5835s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5828s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8164s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5828s for 16384 events => throughput is 6.34E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G15/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.3582s - [COUNTERS] Fortran Other ( 0 ) : 0.0341s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3402s for 183011 events => throughput is 5.38E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0784s for 81920 events => throughput is 1.05E+06 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0775s for 16384 events => throughput is 2.12E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0347s for 16384 events => throughput is 4.72E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0631s for 16384 events => throughput is 2.60E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0998s for 183011 events => throughput is 1.83E+06 events/s + [COUNTERS] PROGRAM TOTAL : 3.2528s + [COUNTERS] Fortran Other ( 0 ) : 0.0351s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2341s for 183011 events => throughput is 7.82E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0777s for 81920 events => throughput is 1.05E+06 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0774s for 16384 events => throughput is 2.12E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0652s for 16384 events => throughput is 2.51E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0993s for 183011 events => throughput is 1.84E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5816s for 16384 events => throughput is 6.35E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7767s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5816s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5814s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6715s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5814s for 16384 events => throughput is 6.35E+03 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/G69/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.2907s - [COUNTERS] Fortran Other ( 0 ) : 0.0369s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3473s for 193329 events => throughput is 5.57E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0690s for 49152 events => throughput is 7.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0797s for 16384 events => throughput is 2.06E+05 events/s + [COUNTERS] PROGRAM TOTAL : 3.1840s + [COUNTERS] Fortran Other ( 0 ) : 0.0370s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2334s for 193329 events => throughput is 8.28E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0693s for 49152 events => throughput is 7.09E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0793s for 16384 events => throughput is 2.07E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0354s for 16384 events => throughput is 4.63E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0609s for 193329 events => throughput is 3.17E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0355s for 16384 events => throughput is 4.62E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0611s for 193329 events => throughput is 3.16E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.5785s for 16384 events => throughput is 6.35E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7122s - [COUNTERS] OVERALL MEs ( 32 ) : 2.5785s for 16384 events => throughput is 6.35E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5990s + [COUNTERS] OVERALL MEs ( 32 ) : 2.5850s for 16384 events => throughput is 6.34E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_taptamggd/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 1.1585 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' in 1.0126 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.1479s - [COUNTERS] Fortran Other ( 0 ) : 0.0395s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4428s for 243014 events => throughput is 5.49E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0673s for 49152 events => throughput is 7.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0439s for 16384 events => throughput is 3.74E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.86E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.34E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0413s for 243014 events => throughput is 5.89E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] PROGRAM TOTAL : 1.0022s + [COUNTERS] Fortran Other ( 0 ) : 0.0394s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2969s for 243014 events => throughput is 8.18E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0669s for 49152 events => throughput is 7.34E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0437s for 16384 events => throughput is 3.75E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.88E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0258s for 16384 events => throughput is 6.36E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0420s for 243014 events => throughput is 5.79E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4065s for 16384 events => throughput is 4.03E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7414s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4065s for 16384 events => throughput is 4.03E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4066s for 16384 events => throughput is 4.03E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5956s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4066s for 16384 events => throughput is 4.03E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_dc_epemgdc/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 2.9924 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' in 2.8245 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G51/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4953s - [COUNTERS] Fortran Other ( 0 ) : 0.0317s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2758s for 152585 events => throughput is 5.53E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0802s for 49152 events => throughput is 6.13E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0810s for 16384 events => throughput is 2.02E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.81E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0049s for 16384 events => throughput is 3.37E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0122s for 152585 events => throughput is 1.25E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0070s + [COUNTERS] PROGRAM TOTAL : 1.4041s + [COUNTERS] Fortran Other ( 0 ) : 0.0312s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1858s for 152585 events => throughput is 8.21E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0799s for 49152 events => throughput is 6.16E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0816s for 16384 events => throughput is 2.01E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0048s for 16384 events => throughput is 3.41E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0121s for 152585 events => throughput is 1.26E+07 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0068s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.9270s for 16384 events => throughput is 1.77E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5683s - [COUNTERS] OVERALL MEs ( 32 ) : 0.9270s for 16384 events => throughput is 1.77E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.9264s for 16384 events => throughput is 1.77E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4777s + [COUNTERS] OVERALL MEs ( 32 ) : 0.9264s for 16384 events => throughput is 1.77E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/G62/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.4773s - [COUNTERS] Fortran Other ( 0 ) : 0.0289s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0426s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2234s for 121146 events => throughput is 5.42E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0804s for 49152 events => throughput is 6.12E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0834s for 16384 events => throughput is 1.96E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0204s for 16384 events => throughput is 8.02E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0322s for 121146 events => throughput is 3.76E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.4016s + [COUNTERS] Fortran Other ( 0 ) : 0.0296s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0412s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1501s for 121146 events => throughput is 8.07E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0795s for 49152 events => throughput is 6.18E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0828s for 16384 events => throughput is 1.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0205s for 16384 events => throughput is 8.01E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0321s for 121146 events => throughput is 3.77E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0069s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s [COUNTERS] CudaCpp MEs ( 19 ) : 0.9249s for 16384 events => throughput is 1.77E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5524s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4767s [COUNTERS] OVERALL MEs ( 32 ) : 0.9249s for 16384 events => throughput is 1.77E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_uu_epemguu/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 3.6727 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' in 3.4838 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/G20/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 3.6620s - [COUNTERS] Fortran Other ( 0 ) : 0.0421s + [COUNTERS] PROGRAM TOTAL : 3.4735s + [COUNTERS] Fortran Other ( 0 ) : 0.0419s [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0417s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.6549s for 329671 events => throughput is 5.03E+05 events/s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4647s for 329671 events => throughput is 7.09E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0780s for 49152 events => throughput is 6.30E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0506s for 16384 events => throughput is 3.24E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0511s for 16384 events => throughput is 3.21E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0553s for 16384 events => throughput is 2.96E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0814s for 329671 events => throughput is 4.05E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0072s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0558s for 16384 events => throughput is 2.93E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0811s for 329671 events => throughput is 4.07E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0071s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 2.6167s for 16384 events => throughput is 6.26E+03 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 1.0452s - [COUNTERS] OVERALL MEs ( 32 ) : 2.6167s for 16384 events => throughput is 6.26E+03 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 2.6182s for 16384 events => throughput is 6.26E+03 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8553s + [COUNTERS] OVERALL MEs ( 32 ) : 2.6182s for 16384 events => throughput is 6.26E+03 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gg_taptamguux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 1.2390 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' in 1.0890 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/G7/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.2273s - [COUNTERS] Fortran Other ( 0 ) : 0.0401s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0422s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4927s for 255151 events => throughput is 5.18E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.0785s + [COUNTERS] Fortran Other ( 0 ) : 0.0407s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3433s for 255151 events => throughput is 7.43E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0828s for 81920 events => throughput is 9.89E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0411s for 16384 events => throughput is 3.99E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0339s for 16384 events => throughput is 4.83E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0340s for 16384 events => throughput is 4.82E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0510s for 255151 events => throughput is 5.01E+06 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0412s for 16384 events => throughput is 3.98E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0338s for 16384 events => throughput is 4.85E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0341s for 16384 events => throughput is 4.81E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0508s for 255151 events => throughput is 5.02E+06 events/s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4040s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.8233s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4040s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4043s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6742s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4043s for 16384 events => throughput is 4.05E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_gd_epemudux/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 2.0336 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' in 1.8221 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G12/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 0.9473s - [COUNTERS] Fortran Other ( 0 ) : 0.0338s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0414s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2939s for 159224 events => throughput is 5.42E+05 events/s + [COUNTERS] PROGRAM TOTAL : 0.8530s + [COUNTERS] Fortran Other ( 0 ) : 0.0333s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0415s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.1988s for 159224 events => throughput is 8.01E+05 events/s [COUNTERS] Fortran PDFs ( 4 ) : 0.0700s for 49152 events => throughput is 7.02E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0440s for 16384 events => throughput is 3.72E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 3.00E+06 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0133s for 159224 events => throughput is 1.20E+07 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0443s for 16384 events => throughput is 3.70E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0343s for 16384 events => throughput is 4.78E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0055s for 16384 events => throughput is 2.99E+06 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0132s for 159224 events => throughput is 1.21E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4059s for 16384 events => throughput is 4.04E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5415s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4059s for 16384 events => throughput is 4.04E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4066s for 16384 events => throughput is 4.03E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4464s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4066s for 16384 events => throughput is 4.03E+04 events/s /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/G28/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.0674s + [COUNTERS] PROGRAM TOTAL : 0.9504s [COUNTERS] Fortran Other ( 0 ) : 0.0345s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0413s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3902s for 201854 events => throughput is 5.17E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.97E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0431s for 16384 events => throughput is 3.80E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0344s for 16384 events => throughput is 4.77E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0164s for 16384 events => throughput is 9.98E+05 events/s - [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0276s for 201854 events => throughput is 7.31E+06 events/s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2733s for 201854 events => throughput is 7.38E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0428s for 16384 events => throughput is 3.83E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0342s for 16384 events => throughput is 4.79E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0165s for 16384 events => throughput is 9.95E+05 events/s + [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0275s for 201854 events => throughput is 7.33E+06 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.4039s for 16384 events => throughput is 4.06E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6635s - [COUNTERS] OVERALL MEs ( 32 ) : 0.4039s for 16384 events => throughput is 4.06E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.4041s for 16384 events => throughput is 4.05E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5463s + [COUNTERS] OVERALL MEs ( 32 ) : 0.4041s for 16384 events => throughput is 4.05E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_epemgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 1.5835 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' in 1.4244 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/G16/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.5719s - [COUNTERS] Fortran Other ( 0 ) : 0.0426s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0418s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.4971s for 268443 events => throughput is 5.40E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0698s for 49152 events => throughput is 7.04E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0431s for 16384 events => throughput is 3.80E+05 events/s - [COUNTERS] Fortran Reweight ( 6 ) : 0.0337s for 16384 events => throughput is 4.87E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0093s for 16384 events => throughput is 1.76E+06 events/s + [COUNTERS] PROGRAM TOTAL : 1.4140s + [COUNTERS] Fortran Other ( 0 ) : 0.0423s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0416s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3403s for 268443 events => throughput is 7.89E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0699s for 49152 events => throughput is 7.03E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0433s for 16384 events => throughput is 3.79E+05 events/s + [COUNTERS] Fortran Reweight ( 6 ) : 0.0336s for 16384 events => throughput is 4.87E+05 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0092s for 16384 events => throughput is 1.77E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0204s for 268443 events => throughput is 1.31E+07 events/s [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8085s for 16384 events => throughput is 2.03E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.7633s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8085s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8077s for 16384 events => throughput is 2.03E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.6063s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8077s for 16384 events => throughput is 2.03E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_ud_taptamgud/ajob1' __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event will call launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' __CUDACPP_DEBUG: MultiCore.launch_and_wait starting '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 1.4037 seconds +__CUDACPP_DEBUG: MultiCore.launch_and_wait finished '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' in 1.3035 seconds __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event back from launch_and_wait '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' /data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/G8/GridRun_21_app.log [COUNTERS] *** USING RDTSC-BASED TIMERS *** - [COUNTERS] PROGRAM TOTAL : 1.3930s - [COUNTERS] Fortran Other ( 0 ) : 0.0328s - [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0421s - [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.3146s for 168484 events => throughput is 5.36E+05 events/s - [COUNTERS] Fortran PDFs ( 4 ) : 0.0705s for 49152 events => throughput is 6.98E+05 events/s - [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0672s for 16384 events => throughput is 2.44E+05 events/s + [COUNTERS] PROGRAM TOTAL : 1.2930s + [COUNTERS] Fortran Other ( 0 ) : 0.0323s + [COUNTERS] Fortran Initialise(I/O) ( 1 ) : 0.0419s + [COUNTERS] Fortran PhaseSpaceSampling ( 3 ) : 0.2169s for 168484 events => throughput is 7.77E+05 events/s + [COUNTERS] Fortran PDFs ( 4 ) : 0.0702s for 49152 events => throughput is 7.00E+05 events/s + [COUNTERS] Fortran UpdateScaleCouplings ( 5 ) : 0.0660s for 16384 events => throughput is 2.48E+05 events/s [COUNTERS] Fortran Reweight ( 6 ) : 0.0341s for 16384 events => throughput is 4.80E+05 events/s - [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0032s for 16384 events => throughput is 5.15E+06 events/s + [COUNTERS] Fortran Unweight(LHE-I/O) ( 7 ) : 0.0032s for 16384 events => throughput is 5.10E+06 events/s [COUNTERS] Fortran SamplePutPoint ( 8 ) : 0.0107s for 168484 events => throughput is 1.58E+07 events/s - [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0054s + [COUNTERS] CudaCpp Initialise ( 11 ) : 0.0053s [COUNTERS] CudaCpp Finalise ( 12 ) : 0.0002s - [COUNTERS] CudaCpp MEs ( 19 ) : 0.8124s for 16384 events => throughput is 2.02E+04 events/s - [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.5807s - [COUNTERS] OVERALL MEs ( 32 ) : 0.8124s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] CudaCpp MEs ( 19 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s + [COUNTERS] OVERALL NON-MEs ( 31 ) : 0.4808s + [COUNTERS] OVERALL MEs ( 32 ) : 0.8123s for 16384 events => throughput is 2.02E+04 events/s __CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished dumping logs from '/data/avalassi/GPU2024/madgraph4gpuX/epochX/cudacpp/tlau/gridpacks/pp_dy3j.mad/madevent/SubProcesses/P0_udx_taptamgudx/ajob1' -__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 275.4730 seconds -__CUDACPP_DEBUG: gen_ximprove.launch finished in 276.0319 seconds -__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 276.0325 seconds +__CUDACPP_DEBUG: gen_ximprove_gridpack.get_job_for_event finished in 250.4046 seconds +__CUDACPP_DEBUG: gen_ximprove.launch finished in 250.9875 seconds +__CUDACPP_DEBUG: GridPackCmd.refine4grid finished in 250.9881 seconds __CUDACPP_DEBUG: GridPackCmd.launch (3a) combine_events combine_events __CUDACPP_DEBUG: GridPackCmd.launch (3b) store_events @@ -2117,9 +2117,9 @@ store_events INFO: No version of lhapdf. Can not run systematics computation decay_events -from_cards -__CUDACPP_DEBUG: GridPackCmd.launch finished in 278.6871 seconds +__CUDACPP_DEBUG: GridPackCmd.launch finished in 253.6539 seconds __CUDACPP_DEBUG: GridPackCmd.__init__ back from self.launch DONE write ./events.lhe.gz -END: Thu Aug 22 03:51:36 PM CEST 2024 -ELAPSED: 279 seconds +END: Thu Aug 22 05:05:25 PM CEST 2024 +ELAPSED: 254 seconds