Skip to content

Commit

Permalink
[gpucpp] rerun 78 tput tests, with FPEs enabled, after the upgrade to…
Browse files Browse the repository at this point in the history 
… 3.5.2 - usual failures in ggttg f/m and gqttq f (madgraph5#783), no change in performance

STARTED  AT Thu Nov  9 05:26:21 PM CET 2023
./tput/teeThroughputX.sh -mix -hrd -makej -eemumu -ggtt -ggttg -ggttgg -gqttq -ggttggg -makeclean
ENDED(1) AT Thu Nov  9 05:54:46 PM CET 2023 [Status=2]
./tput/teeThroughputX.sh -flt -hrd -makej -eemumu -ggtt -ggttgg -inlonly -makeclean
ENDED(2) AT Thu Nov  9 06:05:38 PM CET 2023 [Status=0]
./tput/teeThroughputX.sh -makej -eemumu -ggtt -ggttg -gqttq -ggttgg -ggttggg -flt -bridge -makeclean
ENDED(3) AT Thu Nov  9 06:15:05 PM CET 2023 [Status=2]
./tput/teeThroughputX.sh -eemumu -ggtt -ggttgg -flt -rmbhst
ENDED(4) AT Thu Nov  9 06:18:20 PM CET 2023 [Status=0]
./tput/teeThroughputX.sh -eemumu -ggtt -ggttgg -flt -curhst
ENDED(5) AT Thu Nov  9 06:21:32 PM CET 2023 [Status=0]
  • Loading branch information
@valassi
valassi committed Nov 10, 2023
1 parent 56308e9 commit 381424b
Show file tree
Hide file tree
Showing 78 changed files with 3,476 additions and 3,476 deletions.
86 changes: 43 additions & 43 deletions epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
make[1]: Nothing to be done for 'all'.
make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum'

DATE: 2023-11-08_21:15:12
DATE: 2023-11-09_17:36:35

On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
=========================================================================
Expand All @@ -50,14 +50,14 @@ WARNING! CUDACPP_RUNTIME_ENABLEFPE is set: enable Floating Point Exceptions
Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0]
Workflow summary = CUD:DBL+THX:CURDEV+RMBDEV+MESDEV/none+NAVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
EvtsPerSec[Rmb+ME] (23) = ( 7.482370e+07 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 4.785159e+08 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 6.963951e+08 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 7.632744e+07 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 4.846433e+08 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 7.013402e+08 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 0.677103 sec
2,617,238,862 cycles # 2.883 GHz
4,033,048,225 instructions # 1.54 insn per cycle
0.968798898 seconds time elapsed
TOTAL : 0.666402 sec
2,677,197,972 cycles # 3.012 GHz
4,052,373,824 instructions # 1.51 insn per cycle
0.957128261 seconds time elapsed
runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 1
WARNING! CUDACPP_RUNTIME_ENABLEFPE is set: enable Floating Point Exceptions
==PROF== Profiling "sigmaKin": launch__registers_per_thread 166
Expand All @@ -77,14 +77,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/none+NAVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD)
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.115937e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 1.309320e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 1.309320e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.129159e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 1.324668e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 1.324668e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 6.040810 sec
18,355,110,031 cycles # 3.037 GHz
44,036,146,715 instructions # 2.40 insn per cycle
6.046149721 seconds time elapsed
TOTAL : 5.970581 sec
18,294,560,469 cycles # 3.063 GHz
44,035,841,714 instructions # 2.41 insn per cycle
5.975709847 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 433) (avx2: 0) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest.exe
Expand All @@ -104,14 +104,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/sse4+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.614682e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.109953e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.109953e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.674808e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.201099e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.201099e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 4.305087 sec
12,797,655,048 cycles # 2.970 GHz
31,002,550,325 instructions # 2.42 insn per cycle
4.310429047 seconds time elapsed
TOTAL : 4.151985 sec
12,801,375,184 cycles # 3.080 GHz
31,001,968,290 instructions # 2.42 insn per cycle
4.157180427 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 1643) (avx2: 0) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest.exe
Expand All @@ -131,14 +131,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/avx2+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 2.058335e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.864325e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.864325e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 2.097286e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.929276e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.929276e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 3.453382 sec
10,049,928,632 cycles # 2.906 GHz
19,377,949,384 instructions # 1.93 insn per cycle
3.458678566 seconds time elapsed
TOTAL : 3.388202 sec
10,019,877,774 cycles # 2.954 GHz
19,377,611,613 instructions # 1.93 insn per cycle
3.393320382 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 1965) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest.exe
Expand All @@ -158,14 +158,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512y+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 2.139569e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 3.018506e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 3.018506e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 2.171888e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 3.054473e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 3.054473e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 3.335195 sec
9,699,652,158 cycles # 2.904 GHz
18,994,942,569 instructions # 1.96 insn per cycle
3.340655484 seconds time elapsed
TOTAL : 3.283560 sec
9,692,698,438 cycles # 2.948 GHz
19,006,248,514 instructions # 1.96 insn per cycle
3.288694745 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 1689) (512y: 181) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest.exe
Expand All @@ -185,14 +185,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+MESHST/512z+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.800324e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.389989e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.389989e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.836531e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.447502e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.447502e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 3.895197 sec
8,617,547,988 cycles # 2.211 GHz
15,739,004,417 instructions # 1.83 insn per cycle
3.900641958 seconds time elapsed
TOTAL : 3.828285 sec
8,619,412,035 cycles # 2.250 GHz
15,739,302,747 instructions # 1.83 insn per cycle
3.833534805 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 900) (512y: 154) (512z: 1258)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest.exe
Expand Down
86 changes: 43 additions & 43 deletions epochX/cudacpp/tput/logs_eemumu_mad/log_eemumu_mad_d_inl0_hrd0_bridge.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ CUDACPP_BUILDDIR='build.512z_d_inl0_hrd0'
make[1]: Nothing to be done for 'all'.
make[1]: Leaving directory '/data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum'

DATE: 2023-11-08_21:50:38
DATE: 2023-11-09_18:08:58

On itscrd90.cern.ch [CPU: Intel(R) Xeon(R) Silver 4216 CPU] [GPU: 1x Tesla V100S-PCIE-32GB]:
=========================================================================
Expand All @@ -54,14 +54,14 @@ WARNING! Set grid in Bridge (nevt=524288, gpublocks=2048, gputhreads=256, gpublo
Process = SIGMA_SM_EPEM_MUPMUM_CUDA [nvcc 12.0.140 (gcc 11.3.1)] [inlineHel=0] [hardcodePARAM=0]
Workflow summary = CUD:DBL+THX:CURHST+RMBHST+BRDDEV/none+NAVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
EvtsPerSec[Rmb+ME] (23) = ( 4.736559e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 3.745060e+07 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 3.745060e+07 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 4.786999e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 3.766835e+07 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 3.766835e+07 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 2.222962 sec
7,400,904,179 cycles # 2.991 GHz
13,138,789,289 instructions # 1.78 insn per cycle
2.532867460 seconds time elapsed
TOTAL : 2.197852 sec
7,407,513,320 cycles # 3.040 GHz
13,213,549,787 instructions # 1.78 insn per cycle
2.495471586 seconds time elapsed
runNcu /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/gcheck.exe -p 2048 256 1 --bridge
WARNING! CUDACPP_RUNTIME_ENABLEFPE is set: enable Floating Point Exceptions
WARNING! Bridge selected: cannot use RamboDevice, will use RamboHost
Expand All @@ -86,14 +86,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/none+NAVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = SCALAR ('none': ~vector[1], no SIMD)
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.078362e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 1.258405e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 1.258405e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.082808e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 1.262532e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 1.262532e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 6.440995 sec
19,547,511,222 cycles # 3.033 GHz
44,263,760,517 instructions # 2.26 insn per cycle
6.447379338 seconds time elapsed
TOTAL : 6.417727 sec
19,594,664,001 cycles # 3.052 GHz
44,265,878,138 instructions # 2.26 insn per cycle
6.424119903 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 433) (avx2: 0) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.none_d_inl0_hrd0/runTest.exe
Expand All @@ -114,14 +114,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/sse4+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[2] ('sse4': SSE4.2, 128bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.568240e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.019266e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.019266e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.589377e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.044221e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.044221e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 4.623039 sec
14,052,579,459 cycles # 3.037 GHz
31,844,500,266 instructions # 2.27 insn per cycle
4.629479950 seconds time elapsed
TOTAL : 4.559857 sec
14,005,526,343 cycles # 3.068 GHz
31,844,006,198 instructions # 2.27 insn per cycle
4.566322148 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 1643) (avx2: 0) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.sse4_d_inl0_hrd0/runTest.exe
Expand All @@ -142,14 +142,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/avx2+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[4] ('avx2': AVX2, 256bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.863308e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.529884e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.529884e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.929770e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.628189e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.628189e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 4.004138 sec
11,314,763,691 cycles # 2.822 GHz
20,739,815,252 instructions # 1.83 insn per cycle
4.010963262 seconds time elapsed
TOTAL : 3.878054 sec
11,287,723,645 cycles # 2.906 GHz
20,738,072,181 instructions # 1.84 insn per cycle
3.884538371 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 1965) (512y: 0) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.avx2_d_inl0_hrd0/runTest.exe
Expand All @@ -170,14 +170,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512y+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[4] ('512y': AVX512, 256bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.961498e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.695721e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.695721e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 2.014169e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.779352e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.779352e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 3.824549 sec
10,997,567,801 cycles # 2.871 GHz
20,355,988,697 instructions # 1.85 insn per cycle
3.831152322 seconds time elapsed
TOTAL : 3.727856 sec
11,041,223,612 cycles # 2.958 GHz
20,355,670,345 instructions # 1.84 insn per cycle
3.734291913 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 1689) (512y: 181) (512z: 0)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512y_d_inl0_hrd0/runTest.exe
Expand All @@ -198,14 +198,14 @@ Workflow summary = CPP:DBL+CXS:CURHST+RMBHST+BRDHST/512z+CXVBRK
FP precision = DOUBLE (NaN/abnormal=0, zero=0)
Internal loops fptype_sv = VECTOR[8] ('512z': AVX512, 512bit) [cxtype_ref=YES]
OMP threads / `nproc --all` = 1 / 4
EvtsPerSec[Rmb+ME] (23) = ( 1.664769e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.161936e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.161936e+06 ) sec^-1
EvtsPerSec[Rmb+ME] (23) = ( 1.744355e+06 ) sec^-1
EvtsPerSec[MatrixElems] (3) = ( 2.276403e+06 ) sec^-1
EvtsPerSec[MECalcOnly] (3a) = ( 2.276403e+06 ) sec^-1
MeanMatrixElemValue = ( 1.371706e-02 +- 3.270315e-06 ) GeV^0
TOTAL : 4.405341 sec
9,931,414,577 cycles # 2.252 GHz
16,884,401,146 instructions # 1.70 insn per cycle
4.411803387 seconds time elapsed
TOTAL : 4.223001 sec
9,961,082,180 cycles # 2.356 GHz
16,884,642,255 instructions # 1.70 insn per cycle
4.229415228 seconds time elapsed
=Symbols in CPPProcess.o= (~sse4: 0) (avx2: 900) (512y: 154) (512z: 1258)
-------------------------------------------------------------------------
runExe /data/avalassi/GPU2023/madgraph4gpuX/epochX/cudacpp/ee_mumu.mad/SubProcesses/P1_epem_mupmum/build.512z_d_inl0_hrd0/runTest.exe
Expand Down
Loading

0 comments on commit 381424b

Please sign in to comment.