EPYC Tyan Server

AMD EPYC 7543 32-Core testing with a TYAN S8036GM2NE-LE (V2.00.B21 BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2106244-IB-2106230IB35&sro&grr.

EPYC Tyan ServerProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionVulkanUbuntu 20.04.2 LTSFedora Server 34Debian 10.10Debian BullseyeCentOS StreamClear Linux 34770Ubuntu 21.04AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads)TYAN S8036GM2NE-LE (V2.00.B21 BIOS)AMD Starship/Matisse64GB1000GB Western Digital WD_BLACK SN850 1TBASPEEDVE2282 x Broadcom NetXtreme BCM5720 2-port PCIeUbuntu 20.045.8.0-55-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.94.5 Mesa 20.2.6 (LLVM 11.0.0 256 bits)GCC 9.3.0ext41920x10802 x Broadcom NetXtreme BCM5720 PCIeFedora 345.12.11-300.fc34.x86_64 (x86_64)GCC 11.1.1 20210531xfsDebian 104.19.0-17-amd64 (x86_64)GNOME Shell 3.30.2X ServerGCC 8.3.0ext42 x Broadcom NetXtreme BCM5720 2-port PCIeDebian 115.10.0-7-amd64 (x86_64)GNOME Shell 3.38.41.0.2GCC 10.2.1 20210110llvmpipeCentOS Stream 84.18.0-310.el8.x86_64 (x86_64)GNOME Shell 3.32.2X Server + Wayland4.5 Mesa 21.1.1 (LLVM 11.0.0 256 bits)GCC 8.5.0 20210514xfsClear Linux OS 347705.12.8-1045.native (x86_64)GNOME Shell 40.2X Server 1.20.114.5 Mesa 21.1.3 (LLVM 11.1.0 256 bits)GCC 11.1.1 20210621 releases/gcc-11.1.0-335-g2348a458e1 + Clang 11.1.0 + LLVM 11.1.0ext4ASPEEDUbuntu 21.045.11.0-22-generic (x86_64)GNOME Shell 3.38.4X Server + WaylandGCC 10.3.0OpenBenchmarking.orgKernel Details- Ubuntu 20.04.2 LTS: Transparent Huge Pages: madvise- Fedora Server 34: Transparent Huge Pages: madvise- Debian 10.10: Transparent Huge Pages: always- Debian Bullseye: Transparent Huge Pages: always- CentOS Stream: Transparent Huge Pages: always- Clear Linux 34770: Transparent Huge Pages: always- Ubuntu 21.04: Transparent Huge Pages: madviseCompiler Details- Ubuntu 20.04.2 LTS: --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -v - Fedora Server 34: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver- Debian 10.10: --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 -v - Debian Bullseye: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - CentOS Stream: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver- Clear Linux 34770: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=skylake-avx512 - Ubuntu 21.04: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Ubuntu 20.04.2 LTS: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119- Fedora Server 34: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119- Debian 10.10: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119- Debian Bullseye: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119- CentOS Stream: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- Clear Linux 34770: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- Ubuntu 21.04: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Python Details- Ubuntu 20.04.2 LTS: Python 3.8.5- Fedora Server 34: Python 3.9.5- Debian 10.10: Python 2.7.16 + Python 3.7.3- Debian Bullseye: Python 3.9.2- CentOS Stream: Python 3.6.8- Clear Linux 34770: Python 3.9.5- Ubuntu 21.04: Python 3.9.5Security Details- Ubuntu 20.04.2 LTS: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Fedora Server 34: SELinux + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Debian 10.10: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Debian Bullseye: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- CentOS Stream: SELinux + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Clear Linux 34770: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Ubuntu 21.04: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affectedEnvironment Details- Clear Linux 34770: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags -Wa,-mbranches-within-32B-boundaries" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries -fvisibility-inlines-hidden -Wl,--enable-new-dtags" MESA_GLSL_CACHE_DISABLE=0 FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -Wa,-mbranches-within-32B-boundaries" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""

EPYC Tyan Serveropenvkl: vklBenchmarkhpcg: onnx: fcn-resnet101-11 - OpenMP CPUonnx: yolov4 - OpenMP CPUonnx: bertsquad-10 - OpenMP CPUtnn: CPU - DenseNetmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3npb: EP.Dplaidml: No - Inference - ResNet 50 - CPUbuild-llvm: Unix Makefilesonnx: super-resolution-10 - OpenMP CPUbrl-cad: VGR Performance Metricbuild-llvm: Ninjablender: Barbershop - CPU-Onlykripke: blender: Classroom - CPU-Onlybuild-nodejs: Time To Compileminife: Smalltensorflow-lite: SqueezeNetonnx: shufflenet-v2-10 - OpenMP CPUtensorflow-lite: Mobilenet Floatnpb: BT.Cplaidml: No - Inference - VGG19 - CPUtensorflow-lite: Inception V4tensorflow-lite: Mobilenet Quantvpxenc: Speed 0 - Bosphorus 4Ktensorflow-lite: Inception ResNet V2svt-av1: Preset 4 - Bosphorus 4Kospray: San Miguel - Path Tracerplaidml: No - Inference - VGG16 - CPUnpb: SP.Cvpxenc: Speed 5 - Bosphorus 4Koidn: RTLightmap.hdr.4096x4096luxcorerender: Orange Juice - CPUluxcorerender: Danish Mood - CPUluxcorerender: LuxCore Benchmark - CPUbuild-linux-kernel: Time To Compileluxcorerender: DLSC - CPUbuild-godot: Time To Compilegromacs: MPI CPU - water_GMX50_bareblender: BMW27 - CPU-Onlyincompact3d: input.i3d 193 Cells Per Directionbuild-wasmer: Time To Compileluxcorerender: Rainbow Colors and Prism - CPUnamd: ATPase Simulation - 327,506 Atomsxmrig: Monero - 1Mxmrig: Wownero - 1Mnpb: IS.Doidn: RT.ldr_alb_nrm.3840x2160oidn: RT.hdr_alb_nrm.3840x2160svt-av1: Preset 8 - Bosphorus 4Kembree: Pathtracer ISPC - Asian Dragonavifenc: 6, Losslessastcenc: Exhaustivetnn: CPU - MobileNet v2svt-hevc: 1 - Bosphorus 1080pembree: Pathtracer ISPC - Crownospray: NASA Streamlines - Path Tracertnn: CPU - SqueezeNet v1.1npb: FT.Cavifenc: 10, Losslessnpb: CG.Csvt-vp9: VMAF Optimized - Bosphorus 1080pavifenc: 10svt-hevc: 10 - Bosphorus 1080pnumenta-nab: Windowed Gaussiansvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080ptnn: CPU - SqueezeNet v2svt-vp9: Visual Quality Optimized - Bosphorus 1080pospray: Magnetic Reconnection - Path Tracersvt-hevc: 7 - Bosphorus 1080pUbuntu 20.04.2 LTSFedora Server 34Debian 10.10Debian BullseyeCentOS StreamClear Linux 34770Ubuntu 21.0429712.8778932914452907.26624.3612.8493.9476.09421.9544.1442.5722934.269.04286.3754775422481232.758195.7978658979146.51151.64711203.0469192.61086643688.487954.9822.4993669446472.96.168355391.9313.7226.7333234.2813.630.458.294.324.7335.1375.4557.9073.63952.8527.876948061.24116.380.6725221914.923123.11786.820.900.9020.85137.186530.22223.6779290.33724.6533.318712.35269.18247059.686.28729891.71349.163.817458.186.805353.9862.597264.89500282.3829611.7130842774403042.86122.6032.8943.9755.76718.9334.0422.5351601.228.59257.1684884417781209.690196.6478470519146.65137.58810017.7970453.91091143885.720507.5522.1394189246557.76.898370651.9133.7026.9610058.2816.230.488.294.394.6834.0195.4654.9483.64053.1329.036647841.49816.110.673551092.180.960.9618.34537.383827.88123.5167296.54724.7133.389312.35271.39117996.096.18513587.61291.763.620434.07305.1464.811272.55500281.37282752334322822.38026.4713.4824.2426.32623.7364.7202.9069.60223.2645018409125185.201192.5578433118146.09123.13910918.4069846.21106444222.987888.3827.9594240846650.16.058347241.8523.7333.5433843.8513.030.448.334.364.7429.4925.4763.29352.4417.140.6719322334.523003.30.870.8720.71632.441027.237286.25425.1932.587212.5268.0035.323344.932.785537.016.671353.7362.217297.41444.44296.5728711.7941732824243098.33327.6513.7964.0346.20422.5204.6762.6162965.219.61250.5734597420156202.013189.9078112133145.38134.40713355.469107.31128343711.589192.7727.6793225146349.86.528347031.7073.7833.8733101.409.310.468.394.424.7932.0315.4553.4263.75652.5527.701865060.64116.750.6713123576.324478.31731.340.940.8914.87537.315327.39523.4605307.53424.9633.520412.66269.35849076.245.29830352.21256.352.873429.71259.5662.165236.32422.22273.7029312.4586742424272957.06627.5192.9324.2756.77622.0344.3552.5841006.087.59227.7414475406823192.197190.7677631927146.29127.4987928.4087580.8969945933.121314.0427.9294410547417.36.488437801.9593.7433.5910303.9614.890.478.254.404.7431.1345.463.80152.2528.647742645.00717.010.67415958.160.950.9422.40237.228127.00023.9299301.63724.7633.296012.5269.46718869.875.18812924.77303.332.817467.206.293303.0062.620274.02500285.2029219.43052895.45023.7542.9814.0266.53922.3474.4092.2642844.387.74190.9590502153145.8210393.7872315.643840.587029.1528.3494012646345.67.258372542.0713.7634.2033882.2117.600.488.364.474.8031.1655.523.77752.2527.163459817.480.673732177.720.970.9723.91937.345426.15023.5118289.52725.1533.485712.5270.35048459.814.91529639.93298.742.609463.765.938302.6465.828273.38500299.8031912.6926902573953182.60124.4182.7343.9556.90021.6634.3772.4962929.749.38250.2244684419835209.931197.5273584941147.55140.35211861.483600.81019350144.487240.0522.86105295552961.56.239434081.8753.7027.4332826.2214.600.458.304.304.6631.4505.4754.6303.58153.5928.807995540.23116.290.676381984.730.890.8917.80937.005330.51523.5801316.88524.6933.256912.35277.57946810.916.30228970.46251.543.785470.53257.9866.292241.51500284.09OpenBenchmarking.org

OpenVKL

Benchmark: vklBenchmark

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0470140210280350SE +/- 4.35, N = 9SE +/- 2.66, N = 7SE +/- 2.31, N = 3SE +/- 3.51, N = 3SE +/- 1.45, N = 3SE +/- 4.05, N = 9SE +/- 3.71, N = 3293292282287296297319MIN: 1 / MAX: 1453MIN: 1 / MAX: 1157MIN: 1 / MAX: 852MIN: 1 / MAX: 1036MIN: 1 / MAX: 896MIN: 1 / MAX: 1469MIN: 1 / MAX: 1427

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1CentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04510152025SE +/- 0.13, N = 12SE +/- 0.46, N = 12SE +/- 0.64, N = 9SE +/- 0.60, N = 12SE +/- 0.01, N = 3SE +/- 0.83, N = 912.4619.4311.7911.7112.8812.69-lmpi_cxx-lmpi_cxx-lmpi_cxx-lmpi_cxx-lmpi_cxx1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi

ONNX Runtime

Model: fcn-resnet101-11 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPUCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0420406080100SE +/- 2.25, N = 12SE +/- 1.93, N = 12SE +/- 3.37, N = 9SE +/- 3.41, N = 12SE +/- 4.09, N = 9SE +/- 3.71, N = 127475738493901. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPUCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0460120180240300SE +/- 2.69, N = 12SE +/- 4.62, N = 12SE +/- 4.80, N = 9SE +/- 1.96, N = 3SE +/- 4.38, N = 12SE +/- 4.35, N = 122422332822772912571. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

ONNX Runtime

Model: bertsquad-10 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPUCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04100200300400500SE +/- 4.86, N = 3SE +/- 6.36, N = 12SE +/- 4.24, N = 12SE +/- 4.15, N = 12SE +/- 3.78, N = 12SE +/- 5.31, N = 94274324244404453951. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.047001400210028003500SE +/- 3.26, N = 3SE +/- 2.55, N = 3SE +/- 3.53, N = 3SE +/- 9.62, N = 3SE +/- 20.85, N = 3SE +/- 0.81, N = 3SE +/- 50.91, N = 122957.072895.452822.383098.333042.862907.273182.60MIN: 2883.16 / MAX: 3348.08-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 2840.51 / MAX: 3007.47MIN: 2717.84 / MAX: 3264.89MIN: 2905.58 / MAX: 3528.68MIN: 2872.4 / MAX: 3417.28MIN: 2834.03 / MAX: 3318.39MIN: 2922.01 / MAX: 3982.531. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04714212835SE +/- 0.33, N = 3SE +/- 0.24, N = 15SE +/- 0.23, N = 12SE +/- 0.10, N = 15SE +/- 0.14, N = 15SE +/- 0.22, N = 5SE +/- 0.18, N = 327.5223.7526.4727.6522.6024.3624.42MIN: 26.2 / MAX: 115.35-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 22.09 / MAX: 118.52MIN: 23.92 / MAX: 128.7MIN: 25.83 / MAX: 133.2MIN: 21.09 / MAX: 293.57MIN: 23.32 / MAX: 78.89MIN: 23.37 / MAX: 128.041. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.85411.70822.56233.41644.2705SE +/- 0.195, N = 3SE +/- 0.082, N = 15SE +/- 0.086, N = 12SE +/- 0.083, N = 15SE +/- 0.057, N = 15SE +/- 0.077, N = 5SE +/- 0.013, N = 32.9322.9813.4823.7962.8942.8492.734MIN: 2.63 / MAX: 4.03-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 2.55 / MAX: 34.68MIN: 2.98 / MAX: 5.1MIN: 2.99 / MAX: 6.12MIN: 2.55 / MAX: 7.14MIN: 2.57 / MAX: 7.42MIN: 2.67 / MAX: 3.881. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.96191.92382.88573.84764.8095SE +/- 0.051, N = 3SE +/- 0.078, N = 15SE +/- 0.072, N = 12SE +/- 0.107, N = 15SE +/- 0.046, N = 14SE +/- 0.095, N = 5SE +/- 0.025, N = 34.2754.0264.2424.0343.9753.9473.955MIN: 3.78 / MAX: 21.47-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 3.61 / MAX: 7.37MIN: 3.8 / MAX: 6.21MIN: 3.48 / MAX: 7.15MIN: 3.37 / MAX: 43.2MIN: 3.62 / MAX: 5.86MIN: 3.85 / MAX: 8.921. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04246810SE +/- 0.088, N = 3SE +/- 0.116, N = 15SE +/- 0.099, N = 12SE +/- 0.094, N = 15SE +/- 0.049, N = 15SE +/- 0.096, N = 5SE +/- 0.027, N = 36.7766.5396.3266.2045.7676.0946.900MIN: 6.24 / MAX: 13.86-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 5.73 / MAX: 9.75MIN: 5.64 / MAX: 13.73MIN: 5.43 / MAX: 24.5MIN: 5.34 / MAX: 18.22MIN: 5.73 / MAX: 12.28MIN: 6.51 / MAX: 10.521. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04612182430SE +/- 0.43, N = 3SE +/- 0.27, N = 15SE +/- 0.28, N = 12SE +/- 0.38, N = 15SE +/- 0.28, N = 15SE +/- 0.08, N = 5SE +/- 0.25, N = 322.0322.3523.7422.5218.9321.9521.66MIN: 20.86 / MAX: 39.15-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 19.88 / MAX: 62.08MIN: 22.27 / MAX: 64.14MIN: 20.6 / MAX: 109.28MIN: 17.69 / MAX: 159.34MIN: 20.25 / MAX: 89.25MIN: 20.46 / MAX: 205.81. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041.0622.1243.1864.2485.31SE +/- 0.084, N = 3SE +/- 0.046, N = 15SE +/- 0.046, N = 12SE +/- 0.029, N = 15SE +/- 0.035, N = 15SE +/- 0.037, N = 5SE +/- 0.027, N = 34.3554.4094.7204.6764.0424.1444.377MIN: 4.13 / MAX: 5.15-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 3.99 / MAX: 9.37MIN: 4.17 / MAX: 23.32MIN: 4.15 / MAX: 20.3MIN: 3.75 / MAX: 13.49MIN: 4.02 / MAX: 6.05MIN: 4.25 / MAX: 5.481. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.65391.30781.96172.61563.2695SE +/- 0.018, N = 3SE +/- 0.018, N = 15SE +/- 0.055, N = 12SE +/- 0.033, N = 15SE +/- 0.029, N = 15SE +/- 0.027, N = 5SE +/- 0.025, N = 32.5842.2642.9062.6162.5352.5722.496MIN: 2.51 / MAX: 2.98-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 2.14 / MAX: 5.27MIN: 2.52 / MAX: 6.63MIN: 2.33 / MAX: 5.48MIN: 2.28 / MAX: 3.47MIN: 2.44 / MAX: 4.26MIN: 2.41 / MAX: 3.321. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.046001200180024003000SE +/- 15.88, N = 12SE +/- 35.45, N = 12SE +/- 8.37, N = 3SE +/- 28.47, N = 14SE +/- 21.45, N = 13SE +/- 22.22, N = 151006.082844.382965.211601.222934.262929.74-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian Bullseye: Open MPI 4.1.04. Ubuntu 20.04.2 LTS: Open MPI 4.0.35. Ubuntu 21.04: Open MPI 4.1.0

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.043691215SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 47.597.749.609.618.599.049.38

Timed LLVM Compilation

Build System: Unix Makefiles

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0460120180240300SE +/- 0.88, N = 3SE +/- 3.17, N = 3SE +/- 2.32, N = 3SE +/- 1.83, N = 3SE +/- 1.53, N = 3SE +/- 0.65, N = 3227.74223.26250.57257.17286.38250.22

ONNX Runtime

Model: super-resolution-10 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPUCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0411002200330044005500SE +/- 55.13, N = 12SE +/- 96.24, N = 12SE +/- 22.65, N = 3SE +/- 26.74, N = 3SE +/- 34.58, N = 3SE +/- 27.79, N = 34475501845974884477546841. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.2VGR Performance MetricCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0490K180K270K360K450K4068234091254201564177814224814198351. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -pthread -ldl -lm

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0450100150200250SE +/- 0.67, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.77, N = 3SE +/- 0.86, N = 3SE +/- 0.97, N = 3192.20185.20202.01209.69232.76209.93

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.044080120160200SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.98, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 3190.76190.95192.55189.90196.64195.79197.52

Kripke

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0420M40M60M80M100MSE +/- 1319329.81, N = 12SE +/- 571137.88, N = 3SE +/- 2823751.60, N = 12SE +/- 1339128.86, N = 12SE +/- 2249941.31, N = 15SE +/- 1927474.75, N = 15SE +/- 2082274.38, N = 1277631927905021537843311878112133784705197865897973584941-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3 -fopenmp

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04306090120150SE +/- 0.15, N = 3SE +/- 0.38, N = 3SE +/- 0.27, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3146.29145.82146.09145.38146.65146.51147.55

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04306090120150SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.47, N = 3127.50123.14134.41137.59151.65140.35

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.043K6K9K12K15KSE +/- 381.69, N = 12SE +/- 247.03, N = 12SE +/- 241.94, N = 15SE +/- 374.12, N = 12SE +/- 203.18, N = 12SE +/- 260.75, N = 15SE +/- 136.99, N = 157928.4010393.7810918.4013355.4010017.7911203.0411861.40-lmpi_cxx-lmpi_cxx-lmpi_cxx-lmpi_cxx-lmpi_cxx-lmpi_cxx1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0420K40K60K80K100KSE +/- 2095.69, N = 15SE +/- 789.17, N = 3SE +/- 372.87, N = 3SE +/- 292.33, N = 3SE +/- 521.49, N = 3SE +/- 188.81, N = 3SE +/- 2084.38, N = 1587580.872315.669846.269107.370453.969192.683600.8

ONNX Runtime

Model: shufflenet-v2-10 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPUCentOS StreamDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.042K4K6K8K10KSE +/- 110.43, N = 4SE +/- 108.89, N = 3SE +/- 51.39, N = 3SE +/- 78.91, N = 3SE +/- 51.37, N = 3SE +/- 40.87, N = 3969911064112831091110866101931. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0411K22K33K44K55KSE +/- 897.43, N = 13SE +/- 88.65, N = 3SE +/- 96.21, N = 3SE +/- 101.03, N = 3SE +/- 107.46, N = 3SE +/- 161.47, N = 3SE +/- 684.51, N = 1545933.143840.544222.943711.543885.743688.450144.4

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0420K40K60K80K100KSE +/- 4.57, N = 3SE +/- 114.01, N = 3SE +/- 319.12, N = 3SE +/- 44.18, N = 3SE +/- 482.34, N = 9SE +/- 203.96, N = 3SE +/- 108.57, N = 321314.0487029.1587888.3889192.7720507.5587954.9887240.05-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian 10.10: Open MPI 3.1.34. Debian Bullseye: Open MPI 4.1.05. Ubuntu 20.04.2 LTS: Open MPI 4.0.36. Ubuntu 21.04: Open MPI 4.1.0

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04714212835SE +/- 0.25, N = 3SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.24, N = 3SE +/- 0.23, N = 5SE +/- 0.19, N = 3SE +/- 0.15, N = 327.9228.3427.9527.6722.1322.4922.86

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04200K400K600K800K1000KSE +/- 4791.59, N = 3SE +/- 4646.48, N = 3SE +/- 4599.44, N = 3SE +/- 1376.88, N = 3SE +/- 6145.17, N = 3SE +/- 2093.15, N = 3SE +/- 7728.90, N = 159441059401269424089322519418929366941052955

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0411K22K33K44K55KSE +/- 461.80, N = 3SE +/- 12.85, N = 3SE +/- 94.70, N = 3SE +/- 25.57, N = 3SE +/- 170.17, N = 3SE +/- 88.51, N = 3SE +/- 515.28, N = 1547417.346345.646650.146349.846557.746472.952961.5

VP9 libvpx Encoding

Speed: Speed 0 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.487.256.056.526.896.166.23-U_FORTIFY_SOURCE-pipe -fexceptions -fstack-protector -ffat-lto-objects -fno-trapping-math -mtune=skylake-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -std=gnu++11

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04200K400K600K800K1000KSE +/- 2990.07, N = 3SE +/- 2058.27, N = 3SE +/- 156.42, N = 3SE +/- 1598.54, N = 3SE +/- 1783.60, N = 3SE +/- 1339.58, N = 3SE +/- 18410.13, N = 12843780837254834724834703837065835539943408

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.4660.9321.3981.8642.33SE +/- 0.008, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 31.9592.0711.8521.7071.9131.9311.875-O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

OSPray

Demo: San Miguel - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.85051.7012.55153.4024.2525SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.743.763.733.783.703.723.70MIN: 3.23 / MAX: 3.79MIN: 2.79 / MAX: 3.79MIN: 2.99 / MAX: 3.75MIN: 2.73 / MAX: 3.8MIN: 3.01 / MAX: 3.73MIN: 2.87 / MAX: 3.75MIN: 3.53 / MAX: 3.73

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04816243240SE +/- 0.27, N = 3SE +/- 0.24, N = 3SE +/- 0.25, N = 3SE +/- 0.46, N = 3SE +/- 0.19, N = 3SE +/- 0.23, N = 3SE +/- 0.11, N = 333.5934.2033.5433.8726.9626.7327.43

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.047K14K21K28K35KSE +/- 5.32, N = 3SE +/- 66.76, N = 3SE +/- 79.00, N = 3SE +/- 72.73, N = 3SE +/- 44.59, N = 3SE +/- 59.03, N = 3SE +/- 44.33, N = 310303.9633882.2133843.8533101.4010058.2833234.2832826.22-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian 10.10: Open MPI 3.1.34. Debian Bullseye: Open MPI 4.1.05. Ubuntu 20.04.2 LTS: Open MPI 4.0.36. Ubuntu 21.04: Open MPI 4.1.0

VP9 libvpx Encoding

Speed: Speed 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0448121620SE +/- 0.10, N = 15SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 314.8917.6013.039.3116.2313.6314.60-U_FORTIFY_SOURCE-pipe -fexceptions -fstack-protector -ffat-lto-objects -fno-trapping-math -mtune=skylake-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE-U_FORTIFY_SOURCE1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -std=gnu++11

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.1080.2160.3240.4320.54SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.470.480.440.460.480.450.45

LuxCoreRender

Scene: Orange Juice - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04246810SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.258.368.338.398.298.298.30MIN: 7.37 / MAX: 8.69MIN: 7.45 / MAX: 8.82MIN: 7.33 / MAX: 8.83MIN: 7.42 / MAX: 8.88MIN: 7.33 / MAX: 8.74MIN: 7.33 / MAX: 8.75MIN: 7.42 / MAX: 8.8

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041.00582.01163.01744.02325.029SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.404.474.364.424.394.324.30MIN: 1.78 / MAX: 5.12MIN: 1.75 / MAX: 5.18MIN: 1.73 / MAX: 5.08MIN: 1.72 / MAX: 5.11MIN: 1.77 / MAX: 5.1MIN: 1.72 / MAX: 5.09MIN: 1.71 / MAX: 5.01

LuxCoreRender

Scene: LuxCore Benchmark - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041.082.163.244.325.4SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 34.744.804.744.794.684.734.66MIN: 1.79 / MAX: 5.53MIN: 1.84 / MAX: 5.58MIN: 1.76 / MAX: 5.58MIN: 1.84 / MAX: 5.61MIN: 1.77 / MAX: 5.48MIN: 1.81 / MAX: 5.53MIN: 1.72 / MAX: 5.47

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04816243240SE +/- 0.28, N = 7SE +/- 0.26, N = 8SE +/- 0.22, N = 10SE +/- 0.46, N = 3SE +/- 0.40, N = 4SE +/- 0.36, N = 5SE +/- 0.35, N = 431.1331.1729.4932.0334.0235.1431.45

LuxCoreRender

Scene: DLSC - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041.2422.4843.7264.9686.21SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 35.465.525.475.455.465.455.47MIN: 5.27 / MAX: 5.81MIN: 5.4 / MAX: 5.88MIN: 5.25 / MAX: 5.85MIN: 5.34 / MAX: 5.91MIN: 5.31 / MAX: 5.8MIN: 5.34 / MAX: 5.8MIN: 5.32 / MAX: 5.83

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileDebian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041428425670SE +/- 0.36, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.28, N = 3SE +/- 0.64, N = 363.2953.4354.9557.9154.63

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.85521.71042.56563.42084.276SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.007, N = 3SE +/- 0.010, N = 3SE +/- 0.005, N = 33.8013.7773.7563.6403.6393.581-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3 -pthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041224364860SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 352.2552.2552.4452.5553.1352.8553.59

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04714212835SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.20, N = 15SE +/- 0.09, N = 3SE +/- 0.28, N = 6SE +/- 0.19, N = 328.6527.1627.7029.0427.8828.81-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Timed Wasmer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileCentOS StreamDebian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041428425670SE +/- 0.63, N = 3SE +/- 0.57, N = 3SE +/- 0.19, N = 3SE +/- 0.35, N = 3SE +/- 0.24, N = 345.0160.6441.5061.2440.231. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

LuxCoreRender

Scene: Rainbow Colors and Prism - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0448121620SE +/- 0.29, N = 15SE +/- 0.31, N = 15SE +/- 0.30, N = 15SE +/- 0.26, N = 15SE +/- 0.10, N = 3SE +/- 0.19, N = 15SE +/- 0.18, N = 1517.0117.4817.1416.7516.1116.3816.29MIN: 14.75 / MAX: 19.11MIN: 15.46 / MAX: 18.92MIN: 14.81 / MAX: 19.08MIN: 14.5 / MAX: 18.42MIN: 14.68 / MAX: 16.32MIN: 14.52 / MAX: 18.74MIN: 14.52 / MAX: 18.28

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.15220.30440.45660.60880.761SE +/- 0.00027, N = 3SE +/- 0.00015, N = 3SE +/- 0.00019, N = 3SE +/- 0.00045, N = 3SE +/- 0.00051, N = 3SE +/- 0.00041, N = 3SE +/- 0.00361, N = 30.674150.673730.671930.671310.673550.672520.67638

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MDebian 10.10Debian BullseyeUbuntu 20.04.2 LTS5K10K15K20K25KSE +/- 52.41, N = 3SE +/- 32.24, N = 3SE +/- 33.78, N = 322334.523576.321914.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MDebian 10.10Debian BullseyeUbuntu 20.04.2 LTS5K10K15K20K25KSE +/- 79.23, N = 3SE +/- 30.16, N = 3SE +/- 36.32, N = 323003.324478.323123.11. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.045001000150020002500SE +/- 6.10, N = 3SE +/- 43.89, N = 12SE +/- 10.78, N = 3SE +/- 11.91, N = 4SE +/- 8.29, N = 3SE +/- 19.12, N = 3958.162177.721731.341092.181786.821984.73-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian Bullseye: Open MPI 4.1.04. Ubuntu 20.04.2 LTS: Open MPI 4.0.35. Ubuntu 21.04: Open MPI 4.1.0

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.21830.43660.65490.87321.0915SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 6SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.950.970.870.940.960.900.89

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.21830.43660.65490.87321.0915SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 30.940.970.870.890.960.900.89

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04612182430SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 322.4023.9220.7214.8818.3520.8517.81-O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04918273645SE +/- 0.10, N = 3SE +/- 0.26, N = 3SE +/- 0.64, N = 15SE +/- 0.22, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3SE +/- 0.23, N = 337.2337.3532.4437.3237.3837.1937.01MIN: 36.83 / MAX: 37.88MIN: 36.8 / MAX: 38.26MIN: 29.11 / MAX: 37.15MIN: 36.86 / MAX: 38.33MIN: 36.85 / MAX: 38.17MIN: 36.46 / MAX: 37.99MIN: 36.35 / MAX: 38.08

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, LosslessCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04714212835SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.31, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.23, N = 327.0026.1527.2427.4027.8830.2230.521. (CXX) g++ options: -O3 -fPIC -lm

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ExhaustiveCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04612182430SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 323.9323.5123.4623.5223.6823.581. (CXX) g++ options: -O3 -flto -pthread

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0470140210280350SE +/- 0.46, N = 3SE +/- 0.17, N = 3SE +/- 2.75, N = 3SE +/- 3.50, N = 4SE +/- 2.56, N = 3SE +/- 0.71, N = 3SE +/- 3.07, N = 6301.64289.53286.25307.53296.55290.34316.89MIN: 299.49 / MAX: 336.37-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 287.89 / MAX: 295.67MIN: 280.64 / MAX: 370.21MIN: 283.29 / MAX: 381.19MIN: 285.14 / MAX: 355.51MIN: 286.82 / MAX: 344.05MIN: 286.82 / MAX: 389.031. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

SVT-HEVC

Tuning: 1 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04612182430SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 324.7625.1525.1924.9624.7124.6524.69-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04816243240SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 333.3033.4932.5933.5233.3933.3233.26MIN: 32.81 / MAX: 34.03MIN: 33.01 / MAX: 34.11MIN: 32.08 / MAX: 33.4MIN: 33.02 / MAX: 34.41MIN: 32.92 / MAX: 34.19MIN: 32.96 / MAX: 33.96MIN: 32.8 / MAX: 34.12

OSPray

Demo: NASA Streamlines - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.043691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 312.5012.5012.5012.6612.3512.3512.35MIN: 9.71 / MAX: 12.66MIN: 10.1 / MAX: 12.66MIN: 9.8 / MAX: 12.66MIN: 9.8 / MAX: 12.82MIN: 9.26 / MAX: 12.5MIN: 9.26 / MAX: 12.5MIN: 9.26 / MAX: 12.5

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0460120180240300SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.36, N = 3SE +/- 0.57, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3269.47270.35268.00269.36271.39269.18277.58MIN: 269.22 / MAX: 269.91-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 270.03 / MAX: 270.92MIN: 267.47 / MAX: 295.77MIN: 268.62 / MAX: 270.75MIN: 271.08 / MAX: 271.69MIN: 268.98 / MAX: 269.45MIN: 277.01 / MAX: 283.061. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0411K22K33K44K55KSE +/- 49.69, N = 3SE +/- 318.68, N = 3SE +/- 134.89, N = 3SE +/- 43.58, N = 3SE +/- 40.78, N = 3SE +/- 352.28, N = 1118869.8748459.8149076.2417996.0947059.6846810.91-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian Bullseye: Open MPI 4.1.04. Ubuntu 20.04.2 LTS: Open MPI 4.0.35. Ubuntu 21.04: Open MPI 4.1.0

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, LosslessCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04246810SE +/- 0.064, N = 3SE +/- 0.027, N = 3SE +/- 0.079, N = 15SE +/- 0.015, N = 3SE +/- 0.006, N = 3SE +/- 0.060, N = 6SE +/- 0.047, N = 115.1884.9155.3235.2986.1856.2876.3021. (CXX) g++ options: -O3 -fPIC -lm

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CCentOS StreamClear Linux 34770Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.047K14K21K28K35KSE +/- 138.23, N = 4SE +/- 170.00, N = 3SE +/- 246.35, N = 3SE +/- 10.91, N = 3SE +/- 271.73, N = 3SE +/- 408.24, N = 312924.7729639.9330352.2113587.6129891.7128970.46-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz-lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Clear Linux 34770: 3.23. Debian Bullseye: Open MPI 4.1.04. Ubuntu 20.04.2 LTS: Open MPI 4.0.35. Ubuntu 21.04: Open MPI 4.1.0

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0480160240320400SE +/- 3.44, N = 15SE +/- 3.79, N = 3SE +/- 2.58, N = 15SE +/- 2.14, N = 3SE +/- 1.79, N = 3SE +/- 4.22, N = 12SE +/- 3.29, N = 15303.33298.74344.93256.35291.76349.16251.54-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

libavif avifenc

Encoder Speed: 10

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.040.85881.71762.57643.43524.294SE +/- 0.024, N = 15SE +/- 0.031, N = 4SE +/- 0.037, N = 3SE +/- 0.021, N = 15SE +/- 0.030, N = 9SE +/- 0.018, N = 3SE +/- 0.040, N = 52.8172.6092.7852.8733.6203.8173.7851. (CXX) g++ options: -O3 -fPIC -lm

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04120240360480600SE +/- 12.08, N = 12SE +/- 7.76, N = 15SE +/- 6.17, N = 4SE +/- 8.24, N = 15SE +/- 6.12, N = 15SE +/- 12.16, N = 15SE +/- 10.90, N = 12467.20463.76537.01429.71434.07458.18470.53-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianCentOS StreamClear Linux 34770Debian 10.10Ubuntu 20.04.2 LTS246810SE +/- 0.071, N = 3SE +/- 0.065, N = 3SE +/- 0.035, N = 3SE +/- 0.070, N = 36.2935.9386.6716.805

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0480160240320400SE +/- 2.40, N = 3SE +/- 3.98, N = 3SE +/- 1.49, N = 3SE +/- 0.27, N = 3SE +/- 2.17, N = 15SE +/- 2.18, N = 3SE +/- 8.42, N = 15303.00302.64353.73259.56305.14353.98257.98-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2CentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.041530456075SE +/- 0.16, N = 3SE +/- 0.60, N = 7SE +/- 0.67, N = 5SE +/- 0.47, N = 3SE +/- 0.06, N = 3SE +/- 0.31, N = 3SE +/- 0.11, N = 362.6265.8362.2262.1764.8162.6066.29MIN: 62.33 / MAX: 63.1-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 64.59 / MAX: 69.38MIN: 60.94 / MAX: 65.02MIN: 61.16 / MAX: 62.91MIN: 64.62 / MAX: 65.08MIN: 61.94 / MAX: 63.37MIN: 65.53 / MAX: 69.341. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0460120180240300SE +/- 2.06, N = 3SE +/- 2.72, N = 3SE +/- 2.94, N = 3SE +/- 2.63, N = 5SE +/- 2.18, N = 3SE +/- 2.34, N = 3SE +/- 0.95, N = 3274.02273.38297.41236.32272.55264.89241.51-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OSPray

Demo: Magnetic Reconnection - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.04110220330440550SE +/- 0.00, N = 3SE +/- 21.00, N = 15SE +/- 22.22, N = 15500.00500.00444.44422.22500.00500.00500.00MIN: 333.33MIN: 250MIN: 250 / MAX: 500MIN: 200 / MAX: 500MIN: 250MIN: 250MIN: 250

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pCentOS StreamClear Linux 34770Debian 10.10Debian BullseyeFedora Server 34Ubuntu 20.04.2 LTSUbuntu 21.0470140210280350SE +/- 1.92, N = 3SE +/- 3.06, N = 5SE +/- 3.39, N = 3SE +/- 3.08, N = 4SE +/- 2.22, N = 3SE +/- 3.95, N = 3SE +/- 3.52, N = 4285.20299.80296.57273.70281.37282.38284.09-pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Phoronix Test Suite v10.8.4