new-tests-epyc

2 x AMD EPYC 7702 64-Core testing with a AMD DAYTONA_X (RDY1006G BIOS) and ASPEED on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2008224-NE-NEWTESTSE89&grr.

new-tests-epyc ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionAMD EPYC 7452 32-CoreAMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7662 2PEPYC 7662AMD EPYC 7662EPYC 7702EPYC 7702 2PEPYC 7702 2P RunAMD 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 504GB252GBASPEEDAMD EPYC 7232P 8-Core @ 3.10GHz (8 Cores / 16 Threads)126GB252GBAMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads)AMD EPYC 7F32 8-Core @ 3.70GHz (8 Cores / 16 Threads)2 x AMD EPYC 7F32 8-Core @ 3.70GHz (16 Cores / 32 Threads)504GBAMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads)252GB2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads)504GB2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers378GB2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEAMD EPYC 7662 64-Core @ 2.00GHz (64 Cores / 128 Threads)AMD DAYTONA_X (RDY1006G BIOS)AMD Device 1480252GB2 x Mellanox MT27710AMD EPYC 7702 64-Core @ 2.00GHz (64 Cores / 128 Threads)2 x AMD EPYC 7702 64-Core @ 2.00GHz (128 Cores / 256 Threads)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 -vProcessor Details- AMD EPYC 7452 32-Core: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- AMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- 2 x EPYC 7262: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- 2 x EPYC 7262 2P 4c: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7232 2P 4c: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7232P: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7742: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7F32: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7F32 2P: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7F72: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7F72 2P: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- Xeon Platinum 8280 2P: Scaling Governor: intel_pstate performance - CPU Microcode: 0x500002c- EPYC 7662 2P: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7662: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- AMD EPYC 7662: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7702: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7702 2P: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034- EPYC 7702 2P Run: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8301034Security Details- AMD EPYC 7452 32-Core: 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- AMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X: 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- 2 x EPYC 7262: 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- 2 x EPYC 7262 2P 4c: 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- EPYC 7232 2P 4c: 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- EPYC 7232P: 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- EPYC 7742: 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- EPYC 7F32: 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- EPYC 7F32 2P: 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- EPYC 7F72: 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- EPYC 7F72 2P: 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- Xeon Platinum 8280 2P: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- EPYC 7662 2P: 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- EPYC 7662: 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- AMD EPYC 7662: 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- EPYC 7702: 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- EPYC 7702 2P: 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- EPYC 7702 2P Run: 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 affectedPython Details- EPYC 7702 2P Run: Python 2.7.17 + Python 3.6.9

new-tests-epyc mkl-dnn: IP Batch All - f32hugin: Panorama Photo Assistant + Stitching Timegromacs: Water Benchmarkgromacs: Water Benchmarkmkl-dnn: Recurrent Neural Network Training - f32mkl-dnn: Recurrent Neural Network Inference - f32git: Time To Complete Common Git Commandsmkl-dnn: IP Batch All - u8s8f32mkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: IP Batch 1D - f32tesseract-ocr: Time To OCR 7 Imagesnamd: ATPase Simulation - 327,506 Atomsastcenc: Exhaustiveocrmypdf: Processing 60 Page PDF Documentmkl-dnn: Deconvolution Batch deconv_1d - u8s8f32mkl-dnn: IP Batch 1D - u8s8f32astcenc: Thoroughmkl-dnn: Deconvolution Batch deconv_3d - u8s8f32mkl-dnn: Deconvolution Batch deconv_3d - f32AMD EPYC 7452 32-CoreAMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7662 2PEPYC 7662AMD EPYC 7662EPYC 7702EPYC 7702 2PEPYC 7702 2P Run23.92042.985239.64243.666762.87656.23712.118151.7133543.058513.53582.047943.682962.97937.65902.2322.232285.52246.160262.05220.49763.293722.4928569.54391.856523.240974.4806773.37952.0072.003347.31955.345262.96220.68953.405412.4654969.84242.025123.482414.5586468.27990.8120.814310.49341.014266.60944.11745.455495.69566146.6763.310646.921828.0717761.12640.9960.995309.69239.140366.51743.01015.573316.95951148.7983.369076.832238.2184817.35014.8064.799350.22475.022162.05287.97872.021271.5324523.814625.17981.413462.6536246.84281.3651.367267.56333.100054.67733.93874.513453.48222120.4602.746015.534606.3451931.86072.5152.514267.20448.390954.65217.91202.848942.1294860.80811.638842.874364.1146724.26623.1153.117219.99138.108257.35551.36682.137221.6351145.104612.27222.166263.2385617.92425.7045.705373.86787.861157.46579.87492.113152.0219722.959322.30871.378132.0107517.44185.5555.548231.41570.201860.3504.780621.178101.282170.4450022.201970.3301691.184614.6764.65064.0014.6654.66464.0634.5614.55162.85918.400971.6398.0918.055805.174183.64163.446168.3212.863372.0265832.8150.2899423.8521.89613.712747.90499.271.223084.03510OpenBenchmarking.org

oneDNN MKL-DNN

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch All - Data Type: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run1632486480SE +/- 0.02, N = 3SE +/- 0.64, N = 15SE +/- 1.11, N = 15SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 323.9237.6673.3868.2861.1317.3546.8431.8624.2717.9217.4418.40MIN: 22.68MIN: 34.37MIN: 60.33MIN: 65.55MIN: 57.2MIN: 15.72MIN: 45.5MIN: 30.86MIN: 23.46MIN: 15.53MIN: 16.65MIN: 16.011. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Hugin

Panorama Photo Assistant + Stitching Time

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeEPYC 7702 2P Run1632486480SE +/- 0.98, N = 471.64

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water BenchmarkAMD EPYC 7452 32-Core - ASPEED - AMD DAYTONA_X2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7662 2PAMD EPYC 7662EPYC 7702EPYC 7702 2P Run246810SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.009, N = 3SE +/- 0.016, N = 3SE +/- 0.019, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.036, N = 32.9792.2322.0070.8120.9964.8061.3652.5153.1155.7045.5554.6764.6654.5618.0911. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020Water BenchmarkAMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7662 2PAMD EPYC 7662EPYC 7702EPYC 7702 2P Run246810SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.009, N = 3SE +/- 0.004, N = 3SE +/- 0.021, N = 3SE +/- 0.008, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.035, N = 32.9852.2322.0030.8140.9954.7991.3672.5143.1175.7055.5484.6504.6644.5518.0551. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

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: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run2004006008001000SE +/- 0.42, N = 3SE +/- 3.80, N = 15SE +/- 4.77, N = 3SE +/- 0.66, N = 3SE +/- 0.65, N = 3SE +/- 0.79, N = 3SE +/- 0.38, N = 3SE +/- 3.54, N = 15SE +/- 0.75, N = 3SE +/- 1.73, N = 3SE +/- 1.38, N = 3SE +/- 6.63, N = 15239.64285.52347.32310.49309.69350.22267.56267.20219.99373.87231.42805.17MIN: 235.95MIN: 261.39MIN: 316.21MIN: 302.23MIN: 298MIN: 338.9MIN: 264.4MIN: 238.63MIN: 212.32MIN: 347.46MIN: 221.95MIN: 756.711. (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: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run4080120160200SE +/- 0.28, N = 3SE +/- 0.43, N = 3SE +/- 0.83, N = 3SE +/- 0.08, N = 3SE +/- 0.55, N = 3SE +/- 0.65, N = 3SE +/- 0.12, N = 3SE +/- 1.01, N = 14SE +/- 0.21, N = 3SE +/- 1.17, N = 15SE +/- 0.25, N = 3SE +/- 2.07, N = 743.6746.1655.3541.0139.1475.0233.1048.3938.1187.8670.20183.64MIN: 42.41MIN: 42.94MIN: 46.42MIN: 39.59MIN: 36.32MIN: 71.74MIN: 32.6MIN: 41.21MIN: 36.64MIN: 73.43MIN: 65.73MIN: 169.491. (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 CommandsAMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7662 2PAMD EPYC 7662EPYC 7702EPYC 7702 2P Run1530456075SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 362.8862.0562.9666.6166.5262.0554.6854.6557.3657.4760.3564.0064.0662.8663.451. git version 2.17.1

oneDNN MKL-DNN

Harness: IP Batch All - Data Type: u8s8f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch All - Data Type: u8s8f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run4080120160200SE +/- 0.03246, N = 3SE +/- 0.11836, N = 3SE +/- 0.19410, N = 3SE +/- 0.01679, N = 3SE +/- 0.04688, N = 3SE +/- 0.14847, N = 3SE +/- 0.01586, N = 3SE +/- 0.04943, N = 3SE +/- 0.02393, N = 3SE +/- 0.53163, N = 3SE +/- 0.01916, N = 3SE +/- 0.74461, N = 356.2371020.4976020.6895044.1174043.0101087.9787033.9387017.9120051.3668079.874904.78062168.32100MIN: 45.39MIN: 43.46MIN: 42.03MIN: 80.59MIN: 33.33MIN: 35.98MIN: 70.23MIN: 115.891. (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: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run1.2542.5083.7625.0166.27SE +/- 0.00397, N = 3SE +/- 0.03501, N = 15SE +/- 0.03272, N = 15SE +/- 0.03963, N = 3SE +/- 0.04859, N = 3SE +/- 0.01860, N = 15SE +/- 0.04296, N = 3SE +/- 0.03053, N = 15SE +/- 0.02912, N = 3SE +/- 0.04533, N = 15SE +/- 0.00909, N = 3SE +/- 0.03282, N = 32.118153.293723.405415.455495.573312.021274.513452.848942.137222.113151.178102.86337MIN: 1.96MIN: 2.85MIN: 2.89MIN: 5.23MIN: 5.22MIN: 1.76MIN: 4.38MIN: 2.53MIN: 1.99MIN: 1.72MIN: 1.09MIN: 2.641. (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: f32

OpenBenchmarking.orgms, Fewer Is BetteroneDNN MKL-DNN 1.3Harness: IP Batch 1D - Data Type: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run246810SE +/- 0.00424, N = 3SE +/- 0.02763, N = 15SE +/- 0.02772, N = 7SE +/- 0.00498, N = 3SE +/- 2.22474, N = 15SE +/- 0.01951, N = 4SE +/- 0.00139, N = 3SE +/- 0.02920, N = 15SE +/- 0.00915, N = 3SE +/- 0.32289, N = 12SE +/- 0.00100, N = 3SE +/- 0.00561, N = 31.713352.492852.465495.695666.959511.532453.482222.129481.635112.021971.282172.02658MIN: 1.52MIN: 2.1MIN: 2.14MIN: 5.43MIN: 4.35MIN: 1.35MIN: 3.37MIN: 1.84MIN: 1.55MIN: 1.21MIN: 1.891. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Tesseract OCR

Time To OCR 7 Images

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0-beta.1Time To OCR 7 ImagesEPYC 7702 2P Run816243240SE +/- 0.17, N = 332.82

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 7702 2P Run0.06520.13040.19560.26080.326SE +/- 0.00093, N = 30.28994

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveEPYC 7702 2P Run612182430SE +/- 0.02, N = 323.851. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OCRMyPDF

Processing 60 Page PDF Document

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 6.1.2Processing 60 Page PDF DocumentEPYC 7702 2P Run510152025SE +/- 0.05, N = 321.90

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: u8s8f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run306090120150SE +/- 0.177343, N = 3SE +/- 0.086474, N = 3SE +/- 0.137565, N = 3SE +/- 0.012333, N = 3SE +/- 0.450931, N = 3SE +/- 0.005664, N = 3SE +/- 0.112934, N = 3SE +/- 0.155107, N = 3SE +/- 0.073823, N = 3SE +/- 0.194524, N = 3SE +/- 0.002264, N = 3SE +/- 0.018772, N = 343.05850069.54390069.842400146.676000148.79800023.814600120.46000060.80810045.10460022.9593000.44500213.712700MIN: 41.58MIN: 69.18MIN: 69.22MIN: 146.21MIN: 146.28MIN: 120.06MIN: 60.33MIN: 44.071. (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: u8s8f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run1122334455SE +/- 0.00501, N = 3SE +/- 0.01792, N = 3SE +/- 0.02707, N = 15SE +/- 0.00260, N = 3SE +/- 0.00510, N = 3SE +/- 0.06197, N = 3SE +/- 0.00311, N = 3SE +/- 0.02655, N = 3SE +/- 0.01654, N = 3SE +/- 0.08032, N = 3SE +/- 0.00476, N = 3SE +/- 0.38427, N = 313.535801.856522.025123.310643.3690725.179802.746011.6388412.2722022.308702.2019747.90490MIN: 8.64MIN: 23.6MIN: 6.89MIN: 18.97MIN: 32.291. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughEPYC 7702 2P Run3691215SE +/- 0.05, N = 39.271. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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: u8s8f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run246810SE +/- 0.003673, N = 3SE +/- 0.007205, N = 3SE +/- 0.004856, N = 3SE +/- 0.007454, N = 3SE +/- 0.025030, N = 3SE +/- 0.024018, N = 3SE +/- 0.001153, N = 3SE +/- 0.003789, N = 3SE +/- 0.003590, N = 3SE +/- 0.018103, N = 15SE +/- 0.003565, N = 3SE +/- 0.015576, N = 42.0479403.2409703.4824106.9218206.8322301.4134605.5346002.8743602.1662601.3781300.3301691.223080MIN: 1.84MIN: 3.13MIN: 3.32MIN: 6.88MIN: 6.71MIN: 5.48MIN: 2.77MIN: 2.081. (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: f32AMD EPYC 7452 32-Core2 x EPYC 72622 x EPYC 7262 2P 4cEPYC 7232 2P 4cEPYC 7232PEPYC 7742EPYC 7F32EPYC 7F32 2PEPYC 7F72EPYC 7F72 2PXeon Platinum 8280 2PEPYC 7702 2P Run246810SE +/- 0.00936, N = 3SE +/- 0.02841, N = 3SE +/- 0.02833, N = 3SE +/- 0.02188, N = 3SE +/- 0.01268, N = 3SE +/- 0.03001, N = 15SE +/- 0.01747, N = 3SE +/- 0.05522, N = 4SE +/- 0.00622, N = 3SE +/- 0.00054, N = 3SE +/- 0.00441, N = 3SE +/- 0.01972, N = 33.682964.480674.558648.071778.218482.653626.345194.114673.238562.010751.184614.03510MIN: 3.39MIN: 4.19MIN: 4.26MIN: 7.82MIN: 7.89MIN: 2.31MIN: 6.28MIN: 3.64MIN: 2.98MIN: 1.93MIN: 2.791. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Phoronix Test Suite v10.8.4