Pinned host memory #13
Assignees
Labels
Comments
roiser
added
enhancement
|
This is essentially done, eg in https://github.com/roiser/madgraph4gpu/blob/812f7438462c01e1052c4be48cafcdaef104195c/examples/gpu/eemumu_AV/SubProcesses/P1_Sigma_sm_epem_mupmum/check.cc#L189 I introdcued it here and said I was getting a factor 1.5 better throughoput. We could keep this iopen and repeat the timing test just fo rcurisoity... |
|
This is done. We might have similar/related issues in the fortran bridge, but for the SA test this is completed Closing |
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this issue
May 20, 2022
…failing patching file Source/dsample.f Hunk madgraph5#3 FAILED at 181. Hunk madgraph5#4 succeeded at 197 (offset 2 lines). Hunk madgraph5#5 FAILED at 211. Hunk madgraph5#6 succeeded at 893 (offset 3 lines). 2 out of 6 hunks FAILED -- saving rejects to file Source/dsample.f.rej patching file SubProcesses/addmothers.f patching file SubProcesses/cuts.f patching file SubProcesses/makefile Hunk madgraph5#3 FAILED at 61. Hunk madgraph5#4 succeeded at 94 (offset 6 lines). Hunk madgraph5#5 succeeded at 122 (offset 6 lines). 1 out of 5 hunks FAILED -- saving rejects to file SubProcesses/makefile.rej patching file SubProcesses/reweight.f Hunk #1 FAILED at 1782. Hunk #2 succeeded at 1827 (offset 27 lines). Hunk madgraph5#3 succeeded at 1841 (offset 27 lines). Hunk madgraph5#4 succeeded at 1963 (offset 27 lines). 1 out of 4 hunks FAILED -- saving rejects to file SubProcesses/reweight.f.rej patching file auto_dsig.f Hunk madgraph5#6 FAILED at 301. Hunk madgraph5#10 succeeded at 773 with fuzz 2 (offset 4 lines). Hunk madgraph5#11 succeeded at 912 (offset 16 lines). Hunk madgraph5#12 succeeded at 958 (offset 16 lines). Hunk madgraph5#13 succeeded at 971 (offset 16 lines). Hunk madgraph5#14 succeeded at 987 (offset 16 lines). Hunk madgraph5#15 succeeded at 1006 (offset 16 lines). Hunk madgraph5#16 succeeded at 1019 (offset 16 lines). 1 out of 16 hunks FAILED -- saving rejects to file auto_dsig.f.rej patching file driver.f patching file matrix1.f patching file auto_dsig1.f Hunk #2 succeeded at 220 (offset 7 lines). Hunk madgraph5#3 succeeded at 290 (offset 7 lines). Hunk madgraph5#4 succeeded at 453 (offset 8 lines). Hunk madgraph5#5 succeeded at 464 (offset 8 lines).
valassi
added a commit
to valassi/madgraph4gpu
that referenced
this issue
May 17, 2024
…#845 in log_gqttq_mad_f_inl0_hrd0.txt, the rest as expected STARTED AT Thu May 16 01:24:16 AM CEST 2024 (SM tests) ENDED(1) AT Thu May 16 05:58:45 AM CEST 2024 [Status=0] (BSM tests) ENDED(1) AT Thu May 16 06:07:42 AM CEST 2024 [Status=0] 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_eemumu_mad/log_eemumu_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_eemumu_mad/log_eemumu_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttggg_mad/log_ggttggg_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttggg_mad/log_ggttggg_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttggg_mad/log_ggttggg_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttgg_mad/log_ggttgg_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttgg_mad/log_ggttgg_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttgg_mad/log_ggttgg_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttg_mad/log_ggttg_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttg_mad/log_ggttg_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggttg_mad/log_ggttg_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggtt_mad/log_ggtt_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggtt_mad/log_ggtt_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_ggtt_mad/log_ggtt_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_gqttq_mad/log_gqttq_mad_d_inl0_hrd0.txt 18 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_gqttq_mad/log_gqttq_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_gqttq_mad/log_gqttq_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_heftggbb_mad/log_heftggbb_mad_d_inl0_hrd0.txt 1 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_heftggbb_mad/log_heftggbb_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_heftggbb_mad/log_heftggbb_mad_m_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_smeftggtttt_mad/log_smeftggtttt_mad_d_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_smeftggtttt_mad/log_smeftggtttt_mad_f_inl0_hrd0.txt 24 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_smeftggtttt_mad/log_smeftggtttt_mad_m_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggt1t1_mad/log_susyggt1t1_mad_d_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggt1t1_mad/log_susyggt1t1_mad_f_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggt1t1_mad/log_susyggt1t1_mad_m_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggtt_mad/log_susyggtt_mad_d_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggtt_mad/log_susyggtt_mad_f_inl0_hrd0.txt 0 /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/tmad/logs_susyggtt_mad/log_susyggtt_mad_m_inl0_hrd0.txt The new issue madgraph5#845 is the following +Program received signal SIGFPE: Floating-point exception - erroneous arithmetic operation. + +Backtrace for this error: +#0 0x7f2a1a623860 in ??? +#1 0x7f2a1a622a05 in ??? +#2 0x7f2a1a254def in ??? +madgraph5#3 0x7f2a1ae20acc in ??? +madgraph5#4 0x7f2a1acc4575 in ??? +madgraph5#5 0x7f2a1ae1d4c9 in ??? +madgraph5#6 0x7f2a1ae2570d in ??? +madgraph5#7 0x7f2a1ae2afa1 in ??? +madgraph5#8 0x43008b in ??? +madgraph5#9 0x431c10 in ??? +madgraph5#10 0x432d47 in ??? +madgraph5#11 0x433b1e in ??? +madgraph5#12 0x44a921 in ??? +madgraph5#13 0x42ebbf in ??? +madgraph5#14 0x40371e in ??? +madgraph5#15 0x7f2a1a23feaf in ??? +madgraph5#16 0x7f2a1a23ff5f in ??? +madgraph5#17 0x403844 in ??? +madgraph5#18 0xffffffffffffffff in ??? +./madX.sh: line 379: 3004240 Floating point exception(core dumped) $timecmd $cmd < ${tmpin} > ${tmp} +ERROR! ' ./build.512z_f_inl0_hrd0/madevent_cpp < /tmp/avalassi/input_gqttq_x10_cudacpp > /tmp/avalassi/output_gqttq_x10_cudacpp' failed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Tested by Peter, makes sense for > 3 iterations (still after curand on GPU?)Done also by AV: does speed up copies a lot
in Peters gitlab and eemumu_AV/master
take AV implementation - cudaMallocHost(...)
The text was updated successfully, but these errors were encountered: