new-tests-epyc

2 x AMD EPYC 7262 8-Core testing with a AMD DAYTONA_X (RDY1006G BIOS) and llvmpipe 504GB on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2004158-NI-NEWTESTSE84&gru&sro.

new-tests-epyc ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionAMD EPYC 7452 32-CoreAMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X2 x EPYC 7262AMD EPYC 7452 32-Core @ 2.35GHz (32 Cores / 64 Threads)AMD DAYTONA_X (RDY1006G BIOS)AMD Device 1480252GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Mellanox MT27710Ubuntu 18.045.3.0-40-generic (x86_64)GNOME Shell 3.28.4X Server 1.20.5modesetting 1.20.5GCC 7.4.0ext41920x10802 x AMD EPYC 7262 8-Core @ 3.20GHz (16 Cores / 32 Threads)504GBllvmpipe 504GBOpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

new-tests-epyc gromacs: Water Benchmarkgromacs: Water Benchmarkmkl-dnn: IP Batch 1D - f32mkl-dnn: IP Batch All - f32mkl-dnn: IP Batch 1D - u8s8f32mkl-dnn: IP Batch All - u8s8f32mkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Deconvolution Batch deconv_3d - f32mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32mkl-dnn: Recurrent Neural Network Training - f32mkl-dnn: Recurrent Neural Network Inference - f32git: Time To Complete Common Git CommandsAMD EPYC 7452 32-CoreAMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X2 x EPYC 72622.9851.7133523.920413.535856.23712.118153.6829643.05852.04794239.64243.666762.8762.9792.2322.2322.4928537.65901.8565220.49763.293724.4806769.54393.24097285.52246.160262.052OpenBenchmarking.org

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020Water Benchmark2 x EPYC 7262AMD EPYC 7452 32-Core0.67161.34322.01482.68643.358SE +/- 0.002, N = 3SE +/- 0.003, N = 32.2322.9851. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water Benchmark2 x EPYC 7262AMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X0.67031.34062.01092.68123.3515SE +/- 0.001, N = 3SE +/- 0.005, N = 32.2322.9791. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

oneDNN MKL-DNN

Harness: IP Batch 1D - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch 1D - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core0.56091.12181.68272.24362.8045SE +/- 0.02763, N = 15SE +/- 0.00424, N = 32.492851.71335MIN: 2.1MIN: 1.521. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch All - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core918273645SE +/- 0.64, N = 15SE +/- 0.02, N = 337.6623.92MIN: 34.37MIN: 22.681. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: IP Batch 1D - Data Type: u8s8f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch 1D - Data Type: u8s8f322 x EPYC 7262AMD EPYC 7452 32-Core3691215SE +/- 0.01792, N = 3SE +/- 0.00501, N = 31.8565213.53580MIN: 8.641. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: IP Batch All - Data Type: u8s8f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch All - Data Type: u8s8f322 x EPYC 7262AMD EPYC 7452 32-Core1326395265SE +/- 0.12, N = 3SE +/- 0.03, N = 320.5056.24MIN: 19.94MIN: 45.391. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Deconvolution Batch deconv_1d - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core0.74111.48222.22332.96443.7055SE +/- 0.03501, N = 15SE +/- 0.00397, N = 33.293722.11815MIN: 2.85MIN: 1.961. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Deconvolution Batch deconv_3d - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core1.00822.01643.02464.03285.041SE +/- 0.02841, N = 3SE +/- 0.00936, N = 34.480673.68296MIN: 4.19MIN: 3.391. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f322 x EPYC 7262AMD EPYC 7452 32-Core1530456075SE +/- 0.09, N = 3SE +/- 0.18, N = 369.5443.06MIN: 69.18MIN: 41.581. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f322 x EPYC 7262AMD EPYC 7452 32-Core0.72921.45842.18762.91683.646SE +/- 0.00720, N = 3SE +/- 0.00367, N = 33.240972.04794MIN: 3.13MIN: 1.841. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Recurrent Neural Network Training - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Recurrent Neural Network Training - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core60120180240300SE +/- 3.80, N = 15SE +/- 0.42, N = 3285.52239.64MIN: 261.39MIN: 235.951. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

oneDNN MKL-DNN

Harness: Recurrent Neural Network Inference - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: Recurrent Neural Network Inference - Data Type: f322 x EPYC 7262AMD EPYC 7452 32-Core1020304050SE +/- 0.43, N = 3SE +/- 0.28, N = 346.1643.67MIN: 42.94MIN: 42.411. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Git

Time To Complete Common Git Commands

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commands2 x EPYC 7262AMD EPYC 7452 32-Core1428425670SE +/- 0.06, N = 3SE +/- 0.09, N = 362.0562.881. git version 2.17.1

Phoronix Test Suite v10.8.4