AMD EPYC 7302 / 7402 / 7502 / 7742 2P vs. Intel Xeon Linux Benchmarks

AMD EPYC 7302, 7402, 7502, 7742 1P and 2P Linux performance benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1909146-AS-XEONROME502&grr.

AMD EPYC 7302 / 7402 / 7502 / 7742 2P vs. Intel Xeon Linux BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280AMD EPYC 7302 16-Core @ 3.00GHz (16 Cores / 32 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Device 1480258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GBVE2282 x Mellanox MT27710Ubuntu 19.045.3.0-999-generic (x86_64) 20190907GNOME Shell 3.32.2X Server 1.20.4modesetting 1.20.43.3 Mesa 19.0.8 (LLVM 8.0 128 bits)GCC 8.3.0ext41920x10802 x AMD EPYC 7302 16-Core @ 3.00GHz (32 Cores / 64 Threads)516096MB280GB INTEL SSDPED1D280GA + 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 504GBAMD EPYC 7402 24-Core @ 2.80GHz (24 Cores / 48 Threads)258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GB2 x AMD EPYC 7402 24-Core @ 2.80GHz (48 Cores / 96 Threads)516096MB280GB INTEL SSDPED1D280GA + 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 504GBAMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads)258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GB2 x AMD EPYC 7502 32-Core @ 2.50GHz (64 Cores / 128 Threads)516096MB280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFDllvmpipe 504GBAMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads)258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GB2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)516096MB280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFD + 64GB Flash Drivellvmpipe 504GB2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MB280GB INTEL SSDPED1D280GAllvmpipe 377GB2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE5.3.0-999-generic (x86_64) 20190902GNOME Shell 3.32.03.3 Mesa 19.0.8 (LLVM 8.0 256 bits)Intel Xeon Platinum 8280 @ 4.00GHz (28 Cores / 56 Threads)192512MBllvmpipe 188GBGNOME Shell 3.32.2OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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- EPYC 7302: Scaling Governor: acpi-cpufreq ondemand- EPYC 7302 2P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7402: Scaling Governor: acpi-cpufreq ondemand- EPYC 7402 2P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7502: Scaling Governor: acpi-cpufreq ondemand- EPYC 7502 2P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7742: Scaling Governor: acpi-cpufreq ondemand- EPYC 7742 2P: Scaling Governor: acpi-cpufreq ondemand- 2 x Xeon Platinum 8280: Scaling Governor: intel_pstate powersave- Xeon Platinum 8280: Scaling Governor: intel_pstate powersaveJava Details- OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)Python Details- Python 2.7.16 + Python 3.7.3Security Details- EPYC 7302: 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- EPYC 7302 2P: 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- EPYC 7402: 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- EPYC 7402 2P: 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- EPYC 7502: 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- EPYC 7502 2P: 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- EPYC 7742: 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- EPYC 7742 2P: 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- 2 x Xeon Platinum 8280: 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- Xeon Platinum 8280: 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

AMD EPYC 7302 / 7402 / 7502 / 7742 2P vs. Intel Xeon Linux Benchmarkspennant: sedovbigpennant: leblancbigbuild-gcc: Time To Compilemkl-dnn: Convolution Batch conv_all - f32mysqlslap: 256mkl-dnn: Deconvolution Batch deconv_all - f32cp2k: Fayalite-FIST Datablender: Barbershop - CPU-Onlymkl-dnn: Convolution Batch conv_googlenet_v3 - f32dacapobench: Tradebeansblender: Pabellon Barcelona - CPU-Onlyasmfish: 1024 Hash Memory, 26 Depthappleseed: Material Testergeekbench: CPU Multi Core - Horizon Detectiongeekbench: CPU Multi Core - Face Detectiongeekbench: CPU Multi Core - Gaussian Blurgeekbench: CPU Multi Coreapache-siege: 250blender: Classroom - CPU-Onlynpb: EP.Dnamd: ATPase Simulation - 327,506 Atomsappleseed: Emilyvpxenc: vpxenc VP9 1080p Video Encodeapache-siege: 200ramspeed: Add - Integerbuild-linux-kernel: Time To Compilemkl-dnn: Convolution Batch conv_3d - f32blender: Fishy Cat - CPU-Onlynpb: BT.Cstockfish: Total Timecompress-7zip: Compress Speed Testgeekbench: CPU Single Core - Horizon Detectiongeekbench: CPU Single Core - Face Detectiongeekbench: CPU Single Core - Gaussian Blurgeekbench: CPU Single Coreappleseed: Disney Materialblender: BMW27 - CPU-Onlymkl-dnn: IP Batch All - f32coremark: CoreMark Size 666 - Iterations Per Secondnpb: LU.Cbuild-llvm: Time To Compilejohn-the-ripper: Blowfishneatbench: CPUtungsten: Water Causticpybench: Total For Average Test Timesmkl-dnn: Deconvolution Batch deconv_1d - f32dacapobench: H2povray: Trace Timenpb: FT.Cnpb: IS.Dmkl-dnn: IP Batch 1D - f32phpbench: PHP Benchmark Suitec-ray: Total Time - 4K, 16 Rays Per Pixelnpb: SP.Bramspeed: Add - Floating Pointramspeed: Copy - Integerramspeed: Triad - Floating Pointramspeed: Average - Integerramspeed: Average - Floating Pointramspeed: Scale - Integerramspeed: Scale - Floating Pointramspeed: Triad - Integerdav1d: Summer Nature 4Kmkl-dnn: Convolution Batch conv_alexnet - f32ramspeed: Copy - Floating Pointx265: H.265 1080p Video Encodingx265: H.265 1080p Video Encodingtungsten: Non-Exponentialtungsten: Volumetric Caustictungsten: Hairnpb: MG.Cnpb: CG.Csvt-av1: 1080p 8-bit YUV To AV1 Video Encodemkl-dnn: Deconvolution Batch deconv_3d - f32svt-vp9: 1080p 8-bit YUV To VP9 Video Encodenpb: EP.Csvt-vp9: 1080p 8-bit YUV To VP9 Video Encodex264: H.264 Video Encodingsvt-hevc: 1080p 8-bit YUV To HEVC Video Encodetachyon: Total TimeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82805283.965088.02833.271804.962252837.03583.02400.29101.566522341.2242909829190.61446.17148.30820.131731282203.03264.66905.391.26580266.24167.5788422.5231058.5341.679.62143.5967014.48425541649653923.508.1863.171005148.04101.34200.24588635.4560960.79203.243130528.9726.00122118.35501628.8835850.791683.6016.6648963738.2337885.1631057.5929203.8433964.5141742.8943434.7436616.0339642.9642014.9021.89243.0340056.6844.9650.556.387.7616.2647694.1415726.6244.764.7993.90903.83272.54131.26258.453.06773.81973.932444464.07726.39238.1060.168395180.3875783369294.33813.17290.471.312882337055.62136.310.66156185.93122.3031601.3048551.0927.405.4882.887660251215091422.838.1962.6099181.2854.63123.291134096.74134.266239827.4025.07122511.08616016.3610.4648936719.3543497.4443050.4545057.6943367.9742865.8037111.2439240.2743074.8317.47131.1541011.8745.0449.205.305.679.6760.683.59116.28319.09156.10328.761.798001.817762.54788.381284.712753829.73539.53284.2070.946701234.1962962855171.87628.73219.671.192351456963.01181.581335.440.89148201.33156.0353380.7247188.3332.736.91101.6961593.156202086814023423.808.3164.331026109.3070.54148.29880326.5575893.42158.544675632.9323.97120714.55545620.6532144.3812.5149529325.6234934.0232628.7030643.7532513.0131476.7731542.8330319.9930363.4732533.4816.78173.4342376.4645.3950.815.745.3012.0046418.6862.783.37120.791354.93358.66154.33343.932.11755.46687.402773454.22607.37179.7741.017573128.52112672179289.191.12415.531.533747729810.6094.410.47061168.22135.7332588.8547397.4822.623.8664.7511390141121842523.108.2863.47100663.4540.5299.981655893.53105.849221631.6323.9712118.90648112.159.5649643013.0249163.7333384.5847841.6242662.2745770.7835318.4039947.2446158.1514.4797.7144392.2045.4749.412.974.857.5571.722.70162.84347.87153.23338.311.33773.001086.902914264.43517.80242.8159.546729199.2978467488172.17751.03266.731.422743743435.78152.520.73872177.55158.4539737.2046972.1129.015.8088.347590352817111923.838.3164.40102686.3460.95124.811109475.30143.435752333.7023.33121211.33575917.3410.4849546620.8032733.5730722.9032721.6931512.9531637.8430338.8140840.9244961.9115.98141.7641305.8943.4848.934.434.6610.3467.003.59128.17374.60151.86360.141.74742.54582.662794150.77574.51164.4534.317564109.24135474285289.171.30501.201.664343631407.5778.170.39054170.50144.4133487.9026566.1320.833.4257.6013907088025503423.308.3163.7399959.8335.4181.212118764.3799.9611099231.5724.1312117.84691410.329.6149591610.8641144.3836670.1837295.0736754.1839326.1533122.5432142.4038563.5713.0476.9132581.3543.7947.862.284.496.5796.822.68191.55345.47148.10335.961.21739.05687.923174056.30535.91168.9537.987422116.92131710538183.681.15465.802.234206737201.4386.250.42879155.06160.5936292.3046852.0522.363.6259.3813312086028057524.108.4565.67104163.5037.3989.751966211.24102.149734534.4321.8012028.07667210.869.5650205211.8532412.1930456.3132327.0331250.2731313.9630005.5330092.9332008.6012.0188.9530614.8444.1548.952.174.336.9798.772.44221.23393.10155.81367.521.09229.27221.49729.59412.042752464.67595.26141.7323.75800974.19239606281287.771.81792.37325.155906634172.6946.336095.900.26393174.45152.1831578.1037575.0516.072.7243.71246543.13241185105350308248.2864.43103357.9926.8489.653719996.54227460.1878.8118346532.5322.3012067.4880508.41109565.864238.5614.655017706.29122309.5332582.4941051.7941250.6131120.0531202.4538045.0630063.3232130.4011.4150.6642321.1245.0348.451.524.285.32100057.1649246.88101.522.75280.226224.78344.13151.15329.820.8172.6465.59890.79383.373711014.601468.23181.4321.1812877124.87134205427194.90622.38396.271.523616536791.8795.004180.640.35906153.5093.9532621.0321.313.3062.53139333.6412404446224114925.108.3142.13113565.9537.8497.371883688.97140938.85104.918496831.7121.6110130.96864811.8245215.3211.5964562914.3170065.5528750.1433865.8429305.6432037.4629431.5429834.3026231.7932104.6618.0948.563371132.7634.887.9115.397.0770212.2763.051.11274.164062.61279.16122.23269.001.267306.737085.78934.35766.424271222.641241.54279.3941.7411177237.5070136822121.86648.40225.171.192373459656.14188.042051.530.70069190.7098.8858824.2131619.4131.228.14104.7073870.936515066513977325.408.3342.53114397.0968.3194.88967330.1574601.52158.804292434.3022.1210171.39783720.7025206.719.6863749727.8832401.0131621.1933402.9831445.1431590.0331495.3131601.2631902.8830867.3021.6594.3332958.9433.3335.445.4210.1211.8637023.8655.381.99367.802075.42370.05114.96319.411.91OpenBenchmarking.org

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802K4K6K8K10KSE +/- 0.28, N = 3SE +/- 0.46, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 3SE +/- 0.71, N = 35283.968001.81229.2772.647306.731. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828017003400510068008500SE +/- 0.22, N = 3SE +/- 1.21, N = 3SE +/- 0.50, N = 3SE +/- 0.01, N = 3SE +/- 0.42, N = 35088.027762.54221.4965.597085.781. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802004006008001000SE +/- 0.02, N = 3SE +/- 1.51, N = 3SE +/- 0.25, N = 3SE +/- 0.62, N = 3SE +/- 0.09, N = 3SE +/- 0.28, N = 3SE +/- 0.34, N = 3SE +/- 0.37, N = 3SE +/- 1.22, N = 3SE +/- 0.34, N = 3833.27773.81788.38755.46773.00742.54739.05729.59890.79934.35

MKL-DNN

Harness: Convolution Batch conv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280400800120016002000SE +/- 2.17, N = 3SE +/- 10.43, N = 3SE +/- 5.74, N = 3SE +/- 7.17, N = 3SE +/- 5.22, N = 3SE +/- 7.44, N = 3SE +/- 7.18, N = 3SE +/- 4.36, N = 9SE +/- 3.45, N = 3SE +/- 9.15, N = 31804.96973.931284.71687.401086.90582.66687.92412.04383.37766.42MIN: 1786.74MIN: 941.49MIN: 1261.37MIN: 667.47MIN: 1063.25MIN: 555.58MIN: 664.32MIN: 364.46MIN: 374.5MIN: 748.211. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MariaDB

Clients: 256

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 256EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828090180270360450SE +/- 0.08, N = 3SE +/- 0.25, N = 3SE +/- 0.11, N = 3SE +/- 0.34, N = 3SE +/- 0.05, N = 3SE +/- 0.25, N = 3SE +/- 0.35, N = 3SE +/- 4.45, N = 3SE +/- 0.32, N = 3SE +/- 0.11, N = 3225244275277291279317275371427-laio-laio-laio-laio-laio-laio-laio1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

MKL-DNN

Harness: Deconvolution Batch deconv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010002000300040005000SE +/- 0.83, N = 3SE +/- 11.59, N = 3SE +/- 21.13, N = 3SE +/- 31.64, N = 3SE +/- 8.32, N = 3SE +/- 57.08, N = 4SE +/- 15.00, N = 3SE +/- 24.40, N = 3SE +/- 8.32, N = 3SE +/- 9.92, N = 32837.034464.073829.733454.224264.434150.774056.302464.671014.601222.64MIN: 2805.29MIN: 3952.66MIN: 3522.13MIN: 2389.86MIN: 3799.97MIN: 3399.96MIN: 3583.31MIN: 2014.81MIN: 954.99MIN: 1167.671. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST DataEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828030060090012001500583.02726.39539.53607.37517.80574.51535.91595.261468.231241.54

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Barbershop - Compute: CPU-OnlyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828090180270360450SE +/- 0.27, N = 3SE +/- 0.29, N = 3SE +/- 0.14, N = 3SE +/- 0.33, N = 3SE +/- 0.42, N = 3SE +/- 0.39, N = 3SE +/- 0.23, N = 3SE +/- 0.21, N = 3SE +/- 0.32, N = 3SE +/- 0.13, N = 3400.29238.10284.20179.77242.81164.45168.95141.73181.43279.39

MKL-DNN

Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020406080100SE +/- 0.45, N = 3SE +/- 0.86, N = 4SE +/- 0.84, N = 3SE +/- 0.64, N = 12SE +/- 0.06, N = 3SE +/- 0.53, N = 12SE +/- 0.31, N = 3SE +/- 0.39, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3101.5660.1670.9441.0159.5434.3137.9823.7521.1841.74MIN: 98.25MIN: 54.39MIN: 68.03MIN: 36.66MIN: 57.98MIN: 30.67MIN: 36.66MIN: 21.63MIN: 20.66MIN: 41.151. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82803K6K9K12K15KSE +/- 91.00, N = 2SE +/- 142.00, N = 3SE +/- 72.00, N = 3SE +/- 11.50, N = 2SE +/- 71.42, N = 3SE +/- 90.84, N = 20SE +/- 184.90, N = 4SE +/- 35.00, N = 4652283956701757367297564742280091287711177

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828070140210280350SE +/- 0.34, N = 3SE +/- 0.95, N = 3SE +/- 0.87, N = 3SE +/- 0.67, N = 3SE +/- 0.85, N = 3SE +/- 0.36, N = 3SE +/- 0.51, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3341.22180.38234.19128.52199.29109.24116.9274.19124.87237.50

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828050M100M150M200M250MSE +/- 236368.34, N = 3SE +/- 765274.16, N = 3SE +/- 110587.02, N = 3SE +/- 1935815.84, N = 3SE +/- 455316.65, N = 3SE +/- 221270.37, N = 3SE +/- 618106.66, N = 3SE +/- 915377.87, N = 3SE +/- 1646110.87, N = 3SE +/- 357133.13, N = 34290982975783369629628551126721797846748813547428513171053823960628113420542770136822

Appleseed

Scene: Material Tester

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828060120180240300190.61294.33171.87289.19172.17289.17183.68287.77194.90121.86

Geekbench

Test: CPU Multi Core - Horizon Detection

OpenBenchmarking.orgGpixels/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Horizon DetectionEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802004006008001000SE +/- 0.44, N = 3SE +/- 8.03, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.43, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 311.69, N = 3SE +/- 1.31, N = 3446.17813.17628.731.12751.031.301.151.81622.38648.40

Geekbench

Test: CPU Multi Core - Face Detection

OpenBenchmarking.orgimages/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Face DetectionEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802004006008001000SE +/- 0.72, N = 3SE +/- 2.97, N = 3SE +/- 0.95, N = 3SE +/- 3.76, N = 3SE +/- 1.88, N = 3SE +/- 18.45, N = 3SE +/- 8.04, N = 3SE +/- 20.44, N = 3SE +/- 19.55, N = 3SE +/- 3.43, N = 3148.30290.47219.67415.53266.73501.20465.80792.37396.27225.17

Geekbench

Test: CPU Multi Core - Gaussian Blur

OpenBenchmarking.orgMpixels/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Gaussian BlurEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802004006008001000SE +/- 1.66, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 323.52, N = 3SE +/- 0.17, N = 3SE +/- 0.00, N = 3820.131.311.191.531.421.662.23325.151.521.19

Geekbench

Test: CPU Multi Core

OpenBenchmarking.orgScore, More Is BetterGeekbench 5.0Test: CPU Multi CoreEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828013K26K39K52K65KSE +/- 48.12, N = 3SE +/- 121.59, N = 3SE +/- 27.67, N = 3SE +/- 292.23, N = 3SE +/- 4.36, N = 3SE +/- 351.73, N = 3SE +/- 217.83, N = 3SE +/- 578.86, N = 3SE +/- 261.35, N = 3SE +/- 78.48, N = 317312288232351437477274374343642067590663616523734

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020K40K60K80K100KSE +/- 2390.80, N = 15SE +/- 1193.02, N = 12SE +/- 1860.01, N = 15SE +/- 331.61, N = 3SE +/- 761.44, N = 15SE +/- 91.71, N = 3SE +/- 128.76, N = 3SE +/- 209.09, N = 3SE +/- 45.40, N = 3SE +/- 748.88, N = 382203.0337055.6256963.0129810.6043435.7831407.5737201.4334172.6936791.8759656.141. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Classroom - Compute: CPU-OnlyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828060120180240300SE +/- 0.22, N = 3SE +/- 0.71, N = 3SE +/- 0.03, N = 3SE +/- 0.26, N = 3SE +/- 0.38, N = 3SE +/- 0.20, N = 3SE +/- 0.21, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 3SE +/- 0.29, N = 3264.66136.31181.5894.41152.5278.1786.2546.3395.00188.04

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828013002600390052006500SE +/- 0.76, N = 3SE +/- 4.05, N = 3SE +/- 4.05, N = 3SE +/- 15.00, N = 3SE +/- 31.76, N = 15905.391335.446095.904180.642051.531. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82800.28480.56960.85441.13921.424SE +/- 0.00187, N = 3SE +/- 0.00045, N = 10SE +/- 0.00027, N = 15SE +/- 0.00020, N = 15SE +/- 0.00033, N = 15SE +/- 0.00023, N = 12SE +/- 0.00043, N = 13SE +/- 0.00086, N = 4SE +/- 0.00019, N = 15SE +/- 0.00040, N = 121.265800.661560.891480.470610.738720.390540.428790.263930.359060.70069

Appleseed

Scene: Emily

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828060120180240300266.24185.93201.33168.22177.55170.50155.06174.45153.50190.70

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video EncodeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82804080120160200SE +/- 1.13, N = 3SE +/- 0.61, N = 3SE +/- 2.53, N = 3SE +/- 0.54, N = 3SE +/- 1.78, N = 3SE +/- 0.55, N = 3SE +/- 1.84, N = 3SE +/- 1.08, N = 3SE +/- 1.16, N = 4SE +/- 0.73, N = 3167.57122.30156.03135.73158.45144.41160.59152.1893.9598.881. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

Apache Siege

Concurrent Users: 200

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2PXeon Platinum 828020K40K60K80K100KSE +/- 1768.41, N = 14SE +/- 343.37, N = 3SE +/- 804.16, N = 15SE +/- 500.75, N = 3SE +/- 1323.20, N = 12SE +/- 297.58, N = 15SE +/- 150.37, N = 3SE +/- 345.21, N = 3SE +/- 141.04, N = 388422.5231601.3053380.7232588.8539737.2033487.9036292.3031578.1058824.211. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

RAMspeed SMP

Type: Add - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010K20K30K40K50K31058.5348551.0947188.3347397.4846972.1126566.1346852.0537575.0532621.0331619.411. (CC) gcc options: -O3 -march=native

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82801020304050SE +/- 0.42, N = 9SE +/- 0.26, N = 13SE +/- 0.25, N = 13SE +/- 0.22, N = 15SE +/- 0.26, N = 13SE +/- 0.25, N = 14SE +/- 0.26, N = 13SE +/- 0.26, N = 14SE +/- 0.32, N = 14SE +/- 0.34, N = 1341.6727.4032.7322.6229.0120.8322.3616.0721.3131.22

MKL-DNN

Harness: Convolution Batch conv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82803691215SE +/- 0.10, N = 3SE +/- 0.08, N = 15SE +/- 0.10, N = 4SE +/- 0.10, N = 12SE +/- 0.02, N = 3SE +/- 0.09, N = 15SE +/- 0.05, N = 4SE +/- 0.05, N = 12SE +/- 0.01, N = 3SE +/- 0.00, N = 39.625.486.913.865.803.423.622.723.308.14MIN: 8.79MIN: 4.49MIN: 6.43MIN: 3.25MIN: 5.54MIN: 2.9MIN: 3.36MIN: 2.07MIN: 3.16MIN: 7.961. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280306090120150SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.19, N = 3SE +/- 0.23, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3143.5982.88101.6964.7588.3457.6059.3843.7162.53104.70

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828050K100K150K200K250KSE +/- 38.96, N = 3SE +/- 493.34, N = 13SE +/- 532.50, N = 3SE +/- 336.00, N = 3SE +/- 127.00, N = 367014.4861593.15246543.13139333.6473870.931. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828050M100M150M200M250MSE +/- 79439.80, N = 3SE +/- 586431.96, N = 3SE +/- 55740.39, N = 3SE +/- 306099.70, N = 3SE +/- 989546.79, N = 3SE +/- 1058297.76, N = 3SE +/- 744994.83, N = 3SE +/- 728055.41, N = 3SE +/- 1914132.95, N = 3SE +/- 269571.66, N = 342554164766025126202086811390141175903528139070880133120860241185105124044462651506651. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828080K160K240K320K400KSE +/- 76.86, N = 3SE +/- 2076.26, N = 3SE +/- 288.78, N = 3SE +/- 345.86, N = 3SE +/- 288.18, N = 3SE +/- 1782.94, N = 3SE +/- 362.39, N = 3SE +/- 3511.50, N = 3SE +/- 3784.31, N = 3SE +/- 762.89, N = 3965391509141402342184251711192550342805753503082411491397731. (CXX) g++ options: -pipe -lpthread

Geekbench

Test: CPU Single Core - Horizon Detection

OpenBenchmarking.orgGpixels/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Horizon DetectionEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280612182430SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 323.5022.8323.8023.1023.8323.3024.1024.0025.1025.40

Geekbench

Test: CPU Single Core - Face Detection

OpenBenchmarking.orgimages/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Face DetectionEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 38.188.198.318.288.318.318.458.288.318.33

Geekbench

Test: CPU Single Core - Gaussian Blur

OpenBenchmarking.orgMpixels/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Gaussian BlurEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82801530456075SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.20, N = 3SE +/- 0.22, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.23, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 363.1762.6064.3363.4764.4063.7365.6764.4342.1342.53

Geekbench

Test: CPU Single Core

OpenBenchmarking.orgScore, More Is BetterGeekbench 5.0Test: CPU Single CoreEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802004006008001000SE +/- 3.84, N = 3SE +/- 3.18, N = 3SE +/- 2.08, N = 3SE +/- 4.33, N = 3SE +/- 0.67, N = 3SE +/- 2.60, N = 3SE +/- 2.73, N = 3SE +/- 0.33, N = 310059911026100610269991041103311351143

Appleseed

Scene: Disney Material

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280306090120150148.0481.28109.3063.4586.3459.8363.5057.9965.9597.09

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: BMW27 - Compute: CPU-OnlyEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020406080100SE +/- 0.29, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3101.3454.6370.5440.5260.9535.4137.3926.8437.8468.31

MKL-DNN

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82804080120160200SE +/- 0.41, N = 3SE +/- 1.25, N = 3SE +/- 0.28, N = 3SE +/- 1.37, N = 3SE +/- 0.17, N = 3SE +/- 0.65, N = 3SE +/- 0.81, N = 3SE +/- 0.76, N = 3SE +/- 0.61, N = 3SE +/- 0.53, N = 3200.24123.29148.2999.98124.8181.2189.7589.6597.3794.88MIN: 157.82MIN: 91.89MIN: 114.1MIN: 74.2MIN: 91.72MIN: 58.01MIN: 67.65MIN: 50.92MIN: 54.14MIN: 62.891. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280800K1600K2400K3200K4000KSE +/- 582.97, N = 3SE +/- 3662.17, N = 3SE +/- 4300.99, N = 3SE +/- 11185.21, N = 3SE +/- 890.96, N = 3SE +/- 11036.87, N = 3SE +/- 2305.83, N = 3SE +/- 4830.15, N = 3SE +/- 22012.17, N = 3SE +/- 3609.18, N = 3588635.451134096.74880326.551655893.531109475.302118764.371966211.243719996.541883688.97967330.151. (CC) gcc options: -O2 -lrt" -lrt

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828050K100K150K200K250KSE +/- 704.59, N = 12SE +/- 54.19, N = 3SE +/- 663.76, N = 3SE +/- 49.20, N = 3SE +/- 126.22, N = 360960.7975893.42227460.18140938.8574601.521. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82804080120160200203.24134.26158.54105.84143.4399.96102.1478.81104.91158.80

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828040K80K120K160K200KSE +/- 5.20, N = 3SE +/- 10.97, N = 3SE +/- 37.99, N = 3SE +/- 83.72, N = 3SE +/- 19.00, N = 3SE +/- 1251.62, N = 12SE +/- 78.55, N = 3SE +/- 2284.55, N = 3SE +/- 349.16, N = 3SE +/- 104.73, N = 331305623984675692216575231109929734518346584968429241. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

NeatBench

Acceleration: CPU

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280816243240SE +/- 0.15, N = 3SE +/- 0.21, N = 3SE +/- 0.42, N = 3SE +/- 0.35, N = 3SE +/- 0.44, N = 3SE +/- 0.18, N = 3SE +/- 0.59, N = 3SE +/- 0.03, N = 3SE +/- 0.29, N = 15SE +/- 0.34, N = 928.9727.4032.9331.6333.7031.5734.4332.5331.7134.30

Tungsten Renderer

Scene: Water Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280612182430SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.22, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 326.0025.0723.9723.9723.3324.1321.8022.3021.6122.12-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828030060090012001500SE +/- 4.37, N = 3SE +/- 1.76, N = 3SE +/- 2.73, N = 3SE +/- 1.86, N = 3SE +/- 6.49, N = 3SE +/- 2.40, N = 3SE +/- 1.15, N = 3SE +/- 2.33, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 31221122512071211121212111202120610131017

MKL-DNN

Harness: Deconvolution Batch deconv_1d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280510152025SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 618.3511.0814.558.9011.337.848.077.480.961.39MIN: 17.89MIN: 10.31MIN: 14.02MIN: 8.19MIN: 10.84MIN: 6.54MIN: 7.28MIN: 5.441. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82802K4K6K8K10KSE +/- 26.52, N = 4SE +/- 42.22, N = 20SE +/- 15.37, N = 4SE +/- 69.00, N = 4SE +/- 58.12, N = 4SE +/- 82.60, N = 6SE +/- 31.31, N = 4SE +/- 101.57, N = 4SE +/- 49.86, N = 4SE +/- 35.53, N = 45016616054566481575969146672805086487837

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280714212835SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 15SE +/- 0.18, N = 3SE +/- 0.03, N = 328.8816.3620.6512.1517.3410.3210.868.4111.8220.70-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020K40K60K80K100KSE +/- 291.22, N = 15SE +/- 198.43, N = 3SE +/- 1046.84, N = 3SE +/- 275.30, N = 3SE +/- 16.47, N = 335850.7932144.38109565.8645215.3225206.711. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7302EPYC 7742 2P9001800270036004500SE +/- 2.98, N = 3SE +/- 5.34, N = 31683.604238.561. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

MKL-DNN

Harness: IP Batch 1D - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828048121620SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.39, N = 15SE +/- 0.13, N = 3SE +/- 0.06, N = 316.6610.4612.519.5610.489.619.5614.6511.599.68MIN: 10.87MIN: 6.31MIN: 7.44MIN: 5.94MIN: 6.37MIN: 5.19MIN: 5.91MIN: 5.72MIN: 6.17MIN: 4.891. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280140K280K420K560K700KSE +/- 1513.77, N = 3SE +/- 1836.74, N = 3SE +/- 2237.29, N = 3SE +/- 918.52, N = 3SE +/- 1317.72, N = 3SE +/- 954.57, N = 3SE +/- 1701.68, N = 3SE +/- 743.85, N = 3SE +/- 1072.19, N = 3SE +/- 4992.48, N = 3489637489367495293496430495466495916502052501770645629637497

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280918273645SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 338.2319.3525.6213.0220.8010.8611.856.2914.3127.881. (CC) gcc options: -lm -lpthread -O3

NAS Parallel Benchmarks

Test / Class: SP.B

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828030K60K90K120K150KSE +/- 88.06, N = 3SE +/- 364.79, N = 15SE +/- 509.65, N = 3SE +/- 112.02, N = 3SE +/- 3.07, N = 337885.1634934.02122309.5370065.5532401.011. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

RAMspeed SMP

Type: Add - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828011K22K33K44K55K31057.5943497.4432628.7049163.7332733.5741144.3832412.1932582.4928750.1431621.191. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82809K18K27K36K45K29203.8443050.4530643.7533384.5830722.9036670.1830456.3141051.7933865.8433402.981. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010K20K30K40K50K33964.5145057.6932513.0147841.6232721.6937295.0732327.0341250.6129305.6431445.141. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82809K18K27K36K45K41742.8943367.9731476.7742662.2731512.9536754.1831250.2731120.0532037.4631590.031. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010K20K30K40K50K43434.7442865.8031542.8345770.7831637.8439326.1531313.9631202.4529431.5431495.311. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82808K16K24K32K40K36616.0337111.2430319.9935318.4030338.8133122.5430005.5338045.0629834.3031601.261. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82809K18K27K36K45K39642.9639240.2730363.4739947.2440840.9232142.4030092.9330063.3226231.7931902.881. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010K20K30K40K50K42014.9043074.8332533.4846158.1544961.9138563.5732008.6032130.4032104.6630867.301. (CC) gcc options: -O3 -march=native

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 4KEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280510152025SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.08, N = 321.8917.4716.7814.4715.9813.0412.0111.4118.0921.651. (CC) gcc options: -pthread

MKL-DNN

Harness: Convolution Batch conv_alexnet - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828050100150200250SE +/- 2.31, N = 3SE +/- 1.36, N = 3SE +/- 2.20, N = 3SE +/- 1.43, N = 4SE +/- 0.93, N = 3SE +/- 0.80, N = 3SE +/- 0.93, N = 3SE +/- 0.78, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3243.03131.15173.4397.71141.7676.9188.9550.6648.5694.33MIN: 239.38MIN: 127.87MIN: 168.22MIN: 93.39MIN: 138.14MIN: 74.11MIN: 85.92MIN: 46.37MIN: 47.37MIN: 93.681. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828010K20K30K40K50K40056.6841011.8742376.4644392.2041305.8932581.3530614.8442321.1233711.0032958.941. (CC) gcc options: -O3 -march=native

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82801020304050SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.25, N = 3SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 344.9645.0445.3945.4743.4843.7944.1545.0332.7633.331. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video EncodingEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82801122334455SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.50, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.67, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 350.5549.2050.8149.4148.9347.8648.9548.4534.8835.441. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Tungsten Renderer

Scene: Non-Exponential

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 15SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.51, N = 15SE +/- 0.14, N = 156.385.305.742.974.432.282.171.527.915.42-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

Tungsten Renderer

Scene: Volumetric Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828048121620SE +/- 0.11, N = 4SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 9SE +/- 0.10, N = 37.765.675.304.854.664.494.334.2815.3910.12-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

Tungsten Renderer

Scene: Hair

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828048121620SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 316.269.6712.007.5510.346.576.975.327.0711.86-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz-march=znver1 -msse4a -mno-avx512f -mno-avx512vl -mno-avx512cd -mno-avx512dq -mno-avx512bw-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a-mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a1. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020K40K60K80K100KSE +/- 184.74, N = 3SE +/- 709.52, N = 15SE +/- 778.03, N = 3SE +/- 187.20, N = 3SE +/- 33.78, N = 347694.1446418.68100057.1670212.2737023.861. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7302EPYC 7742 2P11K22K33K44K55KSE +/- 68.23, N = 3SE +/- 626.10, N = 315726.6249246.881. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video EncodeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828020406080100SE +/- 0.18, N = 3SE +/- 1.01, N = 3SE +/- 0.15, N = 3SE +/- 0.70, N = 3SE +/- 0.30, N = 3SE +/- 1.38, N = 4SE +/- 0.55, N = 3SE +/- 0.27, N = 3SE +/- 0.79, N = 3SE +/- 0.46, N = 344.7660.6862.7871.7267.0096.8298.77101.5263.0555.381. (CXX) g++ options: -O3 -pie -lpthread -lm

MKL-DNN

Harness: Deconvolution Batch deconv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f32EPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82801.07782.15563.23344.31125.389SE +/- 0.04, N = 3SE +/- 0.07, N = 15SE +/- 0.00, N = 3SE +/- 0.12, N = 15SE +/- 0.00, N = 3SE +/- 0.11, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.793.593.372.703.592.682.442.751.111.99MIN: 4.55MIN: 3.08MIN: 3.23MIN: 2.03MIN: 3.44MIN: 2.21MIN: 2.36MIN: 2.55MIN: 1.07MIN: 1.961. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video EncodeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828080160240320400SE +/- 0.43, N = 3SE +/- 1.37, N = 3SE +/- 0.65, N = 3SE +/- 2.18, N = 5SE +/- 0.23, N = 3SE +/- 2.34, N = 3SE +/- 1.55, N = 3SE +/- 3.81, N = 3SE +/- 2.16, N = 15SE +/- 5.00, N = 493.90116.28120.79162.84128.17191.55221.23280.22274.16367.801. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7302EPYC 7402EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828013002600390052006500SE +/- 0.78, N = 3SE +/- 2.59, N = 3SE +/- 12.56, N = 3SE +/- 14.06, N = 3SE +/- 1.06, N = 3903.831354.936224.784062.612075.421. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-09-091080p 8-bit YUV To VP9 Video EncodeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828090180270360450SE +/- 1.48, N = 3SE +/- 5.06, N = 3SE +/- 5.34, N = 3SE +/- 4.60, N = 5SE +/- 3.65, N = 3SE +/- 2.98, N = 3SE +/- 5.14, N = 5SE +/- 4.38, N = 15SE +/- 3.34, N = 6SE +/- 5.00, N = 3272.54319.09358.66347.87374.60345.47393.10344.13279.16370.051. (CC) gcc options: -fPIE -fPIC -flto -O3 -O2 -pie -rdynamic -lpthread -lrt -lm

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 8280306090120150SE +/- 0.16, N = 3SE +/- 0.99, N = 3SE +/- 1.38, N = 3SE +/- 0.99, N = 3SE +/- 0.48, N = 3SE +/- 0.64, N = 3SE +/- 0.18, N = 3SE +/- 1.84, N = 3SE +/- 1.36, N = 7SE +/- 0.73, N = 3131.26156.10154.33153.23151.86148.10155.81151.15122.23114.96-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale-lavformat -lavcodec -lavutil -lswscale1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video EncodeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 828080160240320400SE +/- 1.51, N = 3SE +/- 4.32, N = 3SE +/- 2.17, N = 3SE +/- 2.30, N = 3SE +/- 4.93, N = 3SE +/- 4.13, N = 4SE +/- 1.90, N = 3SE +/- 2.50, N = 15SE +/- 1.47, N = 3SE +/- 3.27, N = 13258.45328.76343.93338.31360.14335.96367.52329.82269.00319.411. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total TimeEPYC 7302EPYC 7302 2PEPYC 7402EPYC 7402 2PEPYC 7502EPYC 7502 2PEPYC 7742EPYC 7742 2P2 x Xeon Platinum 8280Xeon Platinum 82800.68851.3772.06552.7543.4425SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.02, N = 12SE +/- 0.01, N = 33.061.792.111.331.741.211.090.811.261.911. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Phoronix Test Suite v10.8.4