server-cpus-june-2021 Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2106033-IB-SINGLE68975&sro&grs .
server-cpus-june-2021 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution 2 x Xeon Platinum 8380 Xeon Platinum 8380 Xeon Platinum 8380 rest 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 7682GB INTEL SSDPF2KX076TZ llvmpipe VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Ubuntu 21.04 5.13.0-051300rc4-generic (x86_64) 20210530 GNOME Shell 3.38.4 X Server 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits) GCC 10.3.0 ext4 1920x1080 Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads) 252GB ASPEED OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler 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++,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 - Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270 Python Details - 2 x Xeon Platinum 8380, Xeon Platinum 8380: Python 3.9.5 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
server-cpus-june-2021 brl-cad: VGR Performance Metric cpuminer-opt: Magi cpuminer-opt: Garlicoin svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K npb: SP.B npb: SP.C pennant: leblancbig incompact3d: input.i3d 193 Cells Per Direction openfoam: Motorbike 60M npb: MG.C liquid-dsp: 128 - 256 - 57 rocksdb: Rand Read openssl: RSA 4096-bit Performance incompact3d: input.i3d 129 Cells Per Direction aircrack-ng: blender: Classroom - CPU-Only helsing: 14 digit askap: tConvolve MPI - Degridding c-ray: Total Time - 4K, 16 Rays Per Pixel tachyon: Total Time john-the-ripper: Blowfish embree: Pathtracer - Asian Dragon coremark: CoreMark Size 666 - Iterations Per Second relion: Basic - CPU m-queens: Time To Solve liquid-dsp: 160 - 256 - 57 askap: tConvolve MPI - Gridding astcenc: Exhaustive toybrot: TBB primesieve: 1e12 Prime Number Generation npb: EP.D toybrot: OpenMP onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU john-the-ripper: MD5 toybrot: C++ Threads amg: asmfish: 1024 Hash Memory, 26 Depth npb: LU.C namd: ATPase Simulation - 327,506 Atoms mt-dgemm: Sustained Floating-Point Rate stockfish: Total Time incompact3d: X3D-benchmarking input.i3d lulesh: blender: Barbershop - CPU-Only v-ray: CPU rays1bench: Large Scene blender: Pabellon Barcelona - CPU-Only wrf: conus 2.5km toktx: UASTC 4 + Zstd Compression 19 embree: Pathtracer ISPC - Asian Dragon rodinia: OpenMP LavaMD liquid-dsp: 64 - 256 - 57 npb: EP.C xmrig: Wownero - 1M graphics-magick: Sharpen embree: Pathtracer - Asian Dragon Obj xmrig: Monero - 1M blender: BMW27 - CPU-Only gromacs: MPI CPU - water_GMX50_bare embree: Pathtracer - Crown tensorflow-lite: Inception ResNet V2 embree: Pathtracer ISPC - Asian Dragon Obj tensorflow-lite: Inception V4 compress-7zip: Compress Speed Test npb: FT.C npb: CG.C graphics-magick: Enhanced toybrot: C++ Tasks askap: tConvolve MT - Degridding tensorflow-lite: Mobilenet Float luxcorerender: DLSC - CPU embree: Pathtracer ISPC - Crown oidn: RTLightmap.hdr.4096x4096 npb: BT.C tensorflow-lite: Mobilenet Quant tensorflow-lite: SqueezeNet blender: Fishy Cat - CPU-Only povray: Trace Time ebizzy: appleseed: Material Tester oidn: RT.hdr_alb_nrm.3840x2160 nwchem: C240 Buckyball oidn: RT.ldr_alb_nrm.3840x2160 pennant: sedovbig onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU openfoam: Motorbike 30M onednn: Deconvolution Batch shapes_3d - f32 - CPU build-llvm: Ninja onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU luxcorerender: Orange Juice - CPU tungsten: Hair onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU lammps: 20k Atoms svt-hevc: 1 - Bosphorus 1080p cloverleaf: Lagrangian-Eulerian Hydrodynamics luxcorerender: Danish Mood - CPU build-nodejs: Time To Compile qe: AUSURF112 lammps: Rhodopsin Protein graphics-magick: Swirl askap: tConvolve OpenMP - Degridding build-linux-kernel: Time To Compile basis: UASTC Level 3 onednn: IP Shapes 1D - u8s8f32 - CPU keydb: kvazaar: Bosphorus 4K - Very Fast rocksdb: Read While Writing onnx: yolov4 - OpenMP CPU build-ffmpeg: Time To Compile appleseed: Disney Material onednn: IP Shapes 1D - bf16bf16bf16 - CPU build-llvm: Unix Makefiles askap: tConvolve OpenMP - Gridding onednn: IP Shapes 1D - f32 - CPU npb: IS.D onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU rodinia: OpenMP CFD Solver dav1d: Summer Nature 4K mysqlslap: 256 mysqlslap: 512 basis: UASTC Level 2 toktx: UASTC 3 openvkl: vklBenchmark graphics-magick: Noise-Gaussian minife: Small onednn: Recurrent Neural Network Training - f32 - CPU build-imagemagick: Time To Compile onednn: Recurrent Neural Network Training - u8s8f32 - CPU build-godot: Time To Compile plaidml: No - Inference - ResNet 50 - CPU build2: Time To Compile build-mesa: Time To Compile graphics-magick: Rotate toktx: UASTC 3 + Zstd Compression 19 appleseed: Emily onnx: bertsquad-10 - OpenMP CPU rodinia: OpenMP Streamcluster kvazaar: Bosphorus 4K - Ultra Fast onednn: IP Shapes 3D - bf16bf16bf16 - CPU graphics-magick: HWB Color Space dav1d: Chimera 1080p 10-bit tungsten: Non-Exponential tensorflow-lite: NASNet Mobile x265: Bosphorus 4K onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU build-php: Time To Compile svt-hevc: 7 - Bosphorus 1080p onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onnx: shufflenet-v2-10 - OpenMP CPU plaidml: No - Inference - VGG19 - CPU build-gdb: Time To Compile askap: tConvolve MT - Gridding onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: IP Shapes 3D - f32 - CPU plaidml: No - Inference - VGG16 - CPU onnx: fcn-resnet101-11 - OpenMP CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p tungsten: Water Caustic webp2: Quality 100, Lossless Compression avifenc: 6, Lossless webp2: Quality 95, Compression Effort 7 webp2: Quality 75, Compression Effort 7 onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU askap: Hogbom Clean OpenMP svt-vp9: VMAF Optimized - Bosphorus 1080p kripke: webp2: Quality 100, Compression Effort 5 svt-vp9: Visual Quality Optimized - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p openvkl: vklBenchmarkVdbVolume rocksdb: Rand Fill Sync ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping openvkl: vklBenchmarkStructuredVolume build-wasmer: Time To Compile build-apache: Time To Compile astcenc: Exhaustive astcenc: Thorough astcenc: Medium vpxenc: Speed 5 - Bosphorus 1080p vpxenc: Speed 0 - Bosphorus 1080p vpxenc: Speed 5 - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 4K srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: OFDM_Test onnx: super-resolution-10 - OpenMP CPU cpuminer-opt: LBC, LBRY Credits cpuminer-opt: Myriad-Groestl cpuminer-opt: Skeincoin cpuminer-opt: Blake-2 S cpuminer-opt: Deepcoin cpuminer-opt: x25x onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU yafaray: Total Time For Sample Scene luxcorerender: Rainbow Colors and Prism - CPU luxcorerender: LuxCore Benchmark - CPU rodinia: OpenMP Leukocyte 2 x Xeon Platinum 8380 Xeon Platinum 8380 Xeon Platinum 8380 rest 2411587 3651.80 41269 57.416 4.734 123538.14 92499.87 4.707610 11.0581346 103.61 118831.52 3279266667 373831966 17835.8 2.57966831 211019.990 71.11 81.464 18222.5 11.008 13.6825 118869 83.5723 2365407.624214 350.743 11.301 3086533333 20662.0 16.6421 6924 3.693 8890.34 7281 2.08924 10200000 6992 2082103333 171121628 188790.14 0.27064 28.146733 180945380 291.416199 35311.845 103.87 66328 346.31 87.63 9822.727 54.917 107.9025 39.069 3047333333 7939.02 42770.8 672 72.4517 26504.2 28.24 9.063 64.7709 572750 89.6186 666967 355140 100812.54 40188.84 1125 7883 12928.8 32738.9 9.41 75.4967 1.44 198052.38 34155.0 47974.6 44.45 9.257 2035986 177.779916 2.98 1846.8 2.99 14.41379 3.25912 3.56396 14.30 0.839556 127.993 0.190628 0.915086 14.33 5.73331 0.604378 35.989 37.49 10.08 6.97 90.570 1169.15 31.561 2191 24810.2 21.627 15.513 1.26700 541996.24 38.71 9170260 482 16.426 57.396983 2.99485 190.683 18859.8 0.914865 3086.24 0.249611 4.709 532.57 697 664 11.415 4.658 820 732 28391.4 675.163 11.962 675.115 48.068 6.21 57.639 18.712 753 9.111 123.700529 516 7.652 47.84 1.81271 1042 861.39 2.56596 74702.4 28.65 439.372 439.640 35.344 313.93 441.260 8402 33.43 39.835 4997.05 0.363977 1.39717 1.36768 38.51 197 469.70 20.3009 413.223 29.692 218.163 117.573 0.228632 0.438511 1238.71 475.45 178965233 6.251 371.88 584.72 29143044 482191 1354.59 104922070 37.688 19.790 7609 402726 84872 774163 3662348 75061 2725.03 757.062 6.96910 81.513 14.11 6.89 47.443 423324 1346.63 15618 21.801 1.859 50133.58 37645.41 11.32899 24.0432320 224.58 56287.53 1565266667 182180961 8726.8 5.26849863 105477.352 142.20 161.647 9239.59 21.645 26.8736 60553 42.6100 1206142.696836 686.961 22.128 1579300000 10580.9 32.4903 13486 7.166 4593.84 14057 4.02680 5305667 13439 1084411667 89220384 98453.55 0.51889 14.696138 94879448 554.938761 18779.645 195.16 35347 184.56 164.01 18356.463 102.030 58.2919 71.991 1654066667 4334.33 23539.9 370 39.9934 14658.2 51.05 5.017 36.0739 1026060 50.0994 1178463 201596 57275.08 22890.25 641 13726 7452.07 56410.0 5.50 44.1689 0.85 117333.47 57591.0 80455.7 74.51 15.515 1215587 106.17271 1.78 3085.1 1.79 23.84300 5.37652 5.87433 23.49 1.37155 208.651 0.310362 1.48256 8.95 9.15446 0.960174 22.682 23.70 15.92 4.42 142.509 1783.19 20.841 1452 16445.2 32.012 22.870 0.872017 771533.42 27.57 6676556 659 22.316 77.521925 4.03139 256.630 14169.2 1.21203 2333.56 0.329636 6.211 404.27 918 870 14.930 6.013 641 586 23125.0 812.260 14.369 810.358 56.580 7.30 67.161 21.794 867 10.387 140.509089 586 6.762 42.65 2.02106 1159 775.38 2.81248 81669.1 31.23 476.024 476.214 38.269 290.36 475.861 9056 31.06 42.710 5305.67 0.343258 1.45952 1.42703 36.97 204 485.54 20.9080 425.324 30.533 223.969 120.690 0.234327 0.427987 1266.33 485.12 175890300 6.303 370.64 583.64 29092155 481504 1356.01 105023963 37.683 19.788 6381 273780 75707 407502 2476303 33583 1022.32 813.025 4.51612 74.903 14.39 4.50 44.021 19.5959 7.4107 4.8512 25.46 11.80 13.97 5.67 95.9 132.2 71.4 98.3 207.5 306.8 129.6 305.6 174.3 273.2 110.1 279.9 120400000 OpenBenchmarking.org
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric 2 x Xeon Platinum 8380 Xeon Platinum 8380 500K 1000K 1500K 2000K 2500K 2411587 423324 1. (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
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Magi 2 x Xeon Platinum 8380 Xeon Platinum 8380 800 1600 2400 3200 4000 SE +/- 39.37, N = 15 SE +/- 12.34, N = 15 3651.80 1346.63 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Garlicoin 2 x Xeon Platinum 8380 Xeon Platinum 8380 9K 18K 27K 36K 45K SE +/- 585.01, N = 15 SE +/- 181.40, N = 4 41269 15618 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K 2 x Xeon Platinum 8380 Xeon Platinum 8380 13 26 39 52 65 SE +/- 0.11, N = 4 SE +/- 0.05, N = 3 57.42 21.80 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K 2 x Xeon Platinum 8380 Xeon Platinum 8380 1.0652 2.1304 3.1956 4.2608 5.326 SE +/- 0.036, N = 3 SE +/- 0.007, N = 3 4.734 1.859 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 2 x Xeon Platinum 8380 Xeon Platinum 8380 30K 60K 90K 120K 150K SE +/- 276.83, N = 9 SE +/- 122.82, N = 6 123538.14 50133.58 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 74.38, N = 4 SE +/- 75.47, N = 3 92499.87 37645.41 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig 2 x Xeon Platinum 8380 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.011962, N = 7 SE +/- 0.018568, N = 4 4.707610 11.328990 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction 2 x Xeon Platinum 8380 Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.02, N = 4 SE +/- 0.01, N = 3 11.06 24.04 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
OpenFOAM Input: Motorbike 60M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 60M 2 x Xeon Platinum 8380 Xeon Platinum 8380 50 100 150 200 250 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 103.61 224.58 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 30K 60K 90K 120K 150K SE +/- 268.68, N = 11 SE +/- 182.12, N = 9 118831.52 56287.53 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 2 x Xeon Platinum 8380 Xeon Platinum 8380 700M 1400M 2100M 2800M 3500M SE +/- 4603018.33, N = 3 SE +/- 3090487.20, N = 3 3279266667 1565266667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read 2 x Xeon Platinum 8380 Xeon Platinum 8380 80M 160M 240M 320M 400M SE +/- 1003430.17, N = 3 SE +/- 1359270.00, N = 3 373831966 182180961 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance 2 x Xeon Platinum 8380 Xeon Platinum 8380 4K 8K 12K 16K 20K SE +/- 75.18, N = 3 SE +/- 55.43, N = 3 17835.8 8726.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction 2 x Xeon Platinum 8380 Xeon Platinum 8380 1.1854 2.3708 3.5562 4.7416 5.927 SE +/- 0.00858289, N = 9 SE +/- 0.00960015, N = 7 2.57966831 5.26849863 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 2 x Xeon Platinum 8380 Xeon Platinum 8380 50K 100K 150K 200K 250K SE +/- 353.02, N = 3 SE +/- 128.50, N = 3 211019.99 105477.35 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only 2 x Xeon Platinum 8380 Xeon Platinum 8380 30 60 90 120 150 SE +/- 0.11, N = 3 SE +/- 0.25, N = 3 71.11 142.20
Helsing Digit Range: 14 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit 2 x Xeon Platinum 8380 Xeon Platinum 8380 40 80 120 160 200 SE +/- 0.89, N = 3 SE +/- 0.57, N = 3 81.46 161.65 1. (CC) gcc options: -O2 -pthread
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 4K 8K 12K 16K 20K SE +/- 73.04, N = 3 SE +/- 37.57, N = 3 18222.50 9239.59 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.01, N = 5 SE +/- 0.17, N = 3 11.01 21.65 1. (CC) gcc options: -lm -lpthread -O3
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time 2 x Xeon Platinum 8380 Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.05, N = 4 SE +/- 0.07, N = 3 13.68 26.87 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish 2 x Xeon Platinum 8380 Xeon Platinum 8380 30K 60K 90K 120K 150K SE +/- 139.20, N = 3 SE +/- 132.64, N = 3 118869 60553 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.22, N = 5 SE +/- 0.50, N = 4 83.57 42.61 MIN: 69.17 / MAX: 92.21 MIN: 39.84 / MAX: 49.36
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second 2 x Xeon Platinum 8380 Xeon Platinum 8380 500K 1000K 1500K 2000K 2500K SE +/- 1412.48, N = 3 SE +/- 1975.05, N = 3 2365407.62 1206142.70 1. (CC) gcc options: -O2 -lrt" -lrt
RELION Test: Basic - Device: CPU OpenBenchmarking.org Seconds, Fewer Is Better RELION 3.1.1 Test: Basic - Device: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 150 300 450 600 750 SE +/- 1.68, N = 3 SE +/- 1.68, N = 3 350.74 686.96 1. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -lmpi
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.03, N = 5 SE +/- 0.04, N = 3 11.30 22.13 1. (CXX) g++ options: -fopenmp -O2 -march=native
Liquid-DSP Threads: 160 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 160 - Buffer Length: 256 - Filter Length: 57 2 x Xeon Platinum 8380 Xeon Platinum 8380 700M 1400M 2100M 2800M 3500M SE +/- 284800.12, N = 3 SE +/- 2451530.13, N = 3 3086533333 1579300000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 4K 8K 12K 16K 20K SE +/- 93.94, N = 3 SE +/- 49.28, N = 3 20662.0 10580.9 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Exhaustive 2 x Xeon Platinum 8380 Xeon Platinum 8380 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 16.64 32.49 1. (CXX) g++ options: -O3 -flto -pthread
toyBrot Fractal Generator Implementation: TBB OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: TBB 2 x Xeon Platinum 8380 Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 55.68, N = 9 SE +/- 115.12, N = 8 6924 13486 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.4 1e12 Prime Number Generation 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.010, N = 9 SE +/- 0.020, N = 6 3.693 7.166 1. (CXX) g++ options: -O3 -lpthread
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D 2 x Xeon Platinum 8380 Xeon Platinum 8380 2K 4K 6K 8K 10K SE +/- 95.83, N = 5 SE +/- 12.97, N = 3 8890.34 4593.84 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
toyBrot Fractal Generator Implementation: OpenMP OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: OpenMP 2 x Xeon Platinum 8380 Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 8.35, N = 6 SE +/- 13.75, N = 4 7281 14057 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.906 1.812 2.718 3.624 4.53 SE +/- 0.00172, N = 7 SE +/- 0.00912, N = 7 2.08924 4.02680 MIN: 2.03 MIN: 3.98 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 2 x Xeon Platinum 8380 Xeon Platinum 8380 2M 4M 6M 8M 10M SE +/- 14502.87, N = 3 SE +/- 15762.12, N = 3 10200000 5305667 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
toyBrot Fractal Generator Implementation: C++ Threads OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Threads 2 x Xeon Platinum 8380 Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 17.11, N = 6 SE +/- 27.98, N = 4 6992 13439 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 2 x Xeon Platinum 8380 Xeon Platinum 8380 400M 800M 1200M 1600M 2000M SE +/- 1152755.01, N = 3 SE +/- 408650.35, N = 3 2082103333 1084411667 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth 2 x Xeon Platinum 8380 Xeon Platinum 8380 40M 80M 120M 160M 200M SE +/- 1594885.41, N = 12 SE +/- 767934.53, N = 3 171121628 89220384
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 40K 80K 120K 160K 200K SE +/- 58.73, N = 4 SE +/- 47.08, N = 3 188790.14 98453.55 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.1168 0.2336 0.3504 0.4672 0.584 SE +/- 0.00027, N = 3 SE +/- 0.00101, N = 3 0.27064 0.51889
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate 2 x Xeon Platinum 8380 Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.08, N = 6 SE +/- 0.03, N = 4 28.15 14.70 1. (CC) gcc options: -O3 -march=native -fopenmp
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time 2 x Xeon Platinum 8380 Xeon Platinum 8380 40M 80M 120M 160M 200M SE +/- 1599896.72, N = 3 SE +/- 570049.11, N = 3 180945380 94879448 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d 2 x Xeon Platinum 8380 Xeon Platinum 8380 120 240 360 480 600 SE +/- 1.61, N = 3 SE +/- 0.44, N = 3 291.42 554.94 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 2 x Xeon Platinum 8380 Xeon Platinum 8380 8K 16K 24K 32K 40K SE +/- 62.90, N = 4 SE +/- 16.09, N = 5 35311.85 18779.65 1. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only 2 x Xeon Platinum 8380 Xeon Platinum 8380 40 80 120 160 200 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 103.87 195.16
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 14K 28K 42K 56K 70K SE +/- 308.74, N = 3 SE +/- 131.93, N = 3 66328 35347
rays1bench Large Scene OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene 2 x Xeon Platinum 8380 Xeon Platinum 8380 80 160 240 320 400 SE +/- 0.57, N = 8 SE +/- 0.17, N = 7 346.31 184.56
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CPU-Only 2 x Xeon Platinum 8380 Xeon Platinum 8380 40 80 120 160 200 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 87.63 164.01
WRF Input: conus 2.5km OpenBenchmarking.org Seconds, Fewer Is Better WRF 4.2.2 Input: conus 2.5km 2 x Xeon Platinum 8380 Xeon Platinum 8380 4K 8K 12K 16K 20K 9822.73 18356.46 1. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
KTX-Software toktx Settings: UASTC 4 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.27, N = 3 54.92 102.03
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.34, N = 6 SE +/- 0.10, N = 5 107.90 58.29 MIN: 96.18 / MAX: 112.26 MIN: 53.64 / MAX: 61.72
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD 2 x Xeon Platinum 8380 Xeon Platinum 8380 16 32 48 64 80 SE +/- 0.24, N = 3 SE +/- 0.66, N = 3 39.07 71.99 1. (CXX) g++ options: -O2 -lOpenCL
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 2 x Xeon Platinum 8380 Xeon Platinum 8380 700M 1400M 2100M 2800M 3500M SE +/- 4053941.84, N = 3 SE +/- 1039764.93, N = 3 3047333333 1654066667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 2K 4K 6K 8K 10K SE +/- 69.57, N = 15 SE +/- 32.20, N = 11 7939.02 4334.33 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M 2 x Xeon Platinum 8380 Xeon Platinum 8380 9K 18K 27K 36K 45K SE +/- 97.10, N = 3 SE +/- 73.93, N = 3 42770.8 23539.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen 2 x Xeon Platinum 8380 Xeon Platinum 8380 150 300 450 600 750 SE +/- 1.45, N = 3 672 370 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Obj 2 x Xeon Platinum 8380 Xeon Platinum 8380 16 32 48 64 80 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 72.45 39.99 MIN: 62.12 / MAX: 82.66 MIN: 38.39 / MAX: 44.94
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M 2 x Xeon Platinum 8380 Xeon Platinum 8380 6K 12K 18K 24K 30K SE +/- 67.30, N = 3 SE +/- 6.99, N = 3 26504.2 14658.2 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only 2 x Xeon Platinum 8380 Xeon Platinum 8380 12 24 36 48 60 SE +/- 0.23, N = 3 SE +/- 0.09, N = 3 28.24 51.05
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare 2 x Xeon Platinum 8380 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.005, N = 3 SE +/- 0.010, N = 3 9.063 5.017 1. (CXX) g++ options: -O3 -pthread
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown 2 x Xeon Platinum 8380 Xeon Platinum 8380 14 28 42 56 70 SE +/- 0.10, N = 5 SE +/- 0.07, N = 3 64.77 36.07 MIN: 59.87 / MAX: 79.46 MIN: 34.8 / MAX: 40.77
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 2 x Xeon Platinum 8380 Xeon Platinum 8380 200K 400K 600K 800K 1000K SE +/- 1484.41, N = 3 SE +/- 276.22, N = 3 572750 1026060
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.40, N = 3 SE +/- 0.05, N = 3 89.62 50.10 MIN: 70.4 / MAX: 98.44 MIN: 46.69 / MAX: 54.05
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 2 x Xeon Platinum 8380 Xeon Platinum 8380 300K 600K 900K 1200K 1500K SE +/- 2539.56, N = 3 SE +/- 1036.96, N = 3 666967 1178463
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test 2 x Xeon Platinum 8380 Xeon Platinum 8380 80K 160K 240K 320K 400K SE +/- 3489.62, N = 3 SE +/- 596.42, N = 3 355140 201596 1. (CXX) g++ options: -pipe -lpthread
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 106.40, N = 7 SE +/- 41.49, N = 6 100812.54 57275.08 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 9K 18K 27K 36K 45K SE +/- 84.43, N = 8 SE +/- 41.74, N = 6 40188.84 22890.25 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 1125 641 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
toyBrot Fractal Generator Implementation: C++ Tasks OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Tasks 2 x Xeon Platinum 8380 Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 27.45, N = 6 SE +/- 31.23, N = 4 7883 13726 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 404.92, N = 3 SE +/- 5.70, N = 3 12928.80 7452.07 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float 2 x Xeon Platinum 8380 Xeon Platinum 8380 12K 24K 36K 48K 60K SE +/- 83.39, N = 3 SE +/- 122.59, N = 3 32738.9 56410.0
LuxCoreRender Scene: DLSC - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.00, N = 3 9.41 5.50 MIN: 8.72 / MAX: 12.17 MIN: 5.29 / MAX: 6.23
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.26, N = 5 SE +/- 0.09, N = 4 75.50 44.17 MIN: 65.3 / MAX: 94.46 MIN: 42.27 / MAX: 48.76
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.324 0.648 0.972 1.296 1.62 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.44 0.85
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C 2 x Xeon Platinum 8380 Xeon Platinum 8380 40K 80K 120K 160K 200K SE +/- 236.31, N = 4 SE +/- 204.16, N = 3 198052.38 117333.47 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant 2 x Xeon Platinum 8380 Xeon Platinum 8380 12K 24K 36K 48K 60K SE +/- 253.99, N = 12 SE +/- 71.21, N = 3 34155.0 57591.0
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet 2 x Xeon Platinum 8380 Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 433.14, N = 7 SE +/- 65.86, N = 3 47974.6 80455.7
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CPU-Only 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 44.45 74.51
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.039, N = 5 SE +/- 0.041, N = 3 9.257 15.515 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
ebizzy OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 2 x Xeon Platinum 8380 Xeon Platinum 8380 400K 800K 1200K 1600K 2000K SE +/- 19700.68, N = 15 SE +/- 17257.96, N = 15 2035986 1215587 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester 2 x Xeon Platinum 8380 Xeon Platinum 8380 40 80 120 160 200 177.78 106.17
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.6705 1.341 2.0115 2.682 3.3525 SE +/- 0.00, N = 5 SE +/- 0.00, N = 3 2.98 1.78
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball 2 x Xeon Platinum 8380 Xeon Platinum 8380 700 1400 2100 2800 3500 1846.8 3085.1 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.6728 1.3456 2.0184 2.6912 3.364 SE +/- 0.00, N = 5 SE +/- 0.00, N = 3 2.99 1.79
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig 2 x Xeon Platinum 8380 Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.01, N = 4 SE +/- 0.02, N = 3 14.41 23.84 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 1.2097 2.4194 3.6291 4.8388 6.0485 SE +/- 0.00173, N = 3 SE +/- 0.01029, N = 3 3.25912 5.37652 MIN: 3.09 MIN: 5.25 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 1.3217 2.6434 3.9651 5.2868 6.6085 SE +/- 0.00332, N = 9 SE +/- 0.00133, N = 9 3.56396 5.87433 MIN: 3.49 MIN: 5.71 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenFOAM Input: Motorbike 30M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M 2 x Xeon Platinum 8380 Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 14.30 23.49 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.3086 0.6172 0.9258 1.2344 1.543 SE +/- 0.000669, N = 9 SE +/- 0.000612, N = 9 0.839556 1.371550 MIN: 0.8 MIN: 1.31 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja 2 x Xeon Platinum 8380 Xeon Platinum 8380 50 100 150 200 250 SE +/- 0.54, N = 3 SE +/- 0.93, N = 3 127.99 208.65
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.0698 0.1396 0.2094 0.2792 0.349 SE +/- 0.000612, N = 9 SE +/- 0.002283, N = 15 0.190628 0.310362 MIN: 0.18 MIN: 0.29 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.3336 0.6672 1.0008 1.3344 1.668 SE +/- 0.002416, N = 7 SE +/- 0.000981, N = 7 0.915086 1.482560 MIN: 0.85 MIN: 1.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
LuxCoreRender Scene: Orange Juice - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 14.33 8.95 MIN: 11.53 / MAX: 18.29 MIN: 7.51 / MAX: 10.05
Tungsten Renderer Scene: Hair OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair 2 x Xeon Platinum 8380 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.05061, N = 8 SE +/- 0.04039, N = 5 5.73331 9.15446 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.216 0.432 0.648 0.864 1.08 SE +/- 0.001365, N = 4 SE +/- 0.001560, N = 4 0.604378 0.960174 MIN: 0.56 MIN: 0.91 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: 20k Atoms 2 x Xeon Platinum 8380 Xeon Platinum 8380 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 35.99 22.68 1. (CXX) g++ options: -O3 -pthread -lm
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.32, N = 3 SE +/- 0.06, N = 3 37.49 23.70 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.04, N = 5 SE +/- 0.01, N = 4 10.08 15.92 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
LuxCoreRender Scene: Danish Mood - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 6.97 4.42 MIN: 3.13 / MAX: 8.11 MIN: 1.74 / MAX: 5.11
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.25, N = 3 90.57 142.51
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.7 Input: AUSURF112 2 x Xeon Platinum 8380 Xeon Platinum 8380 400 800 1200 1600 2000 SE +/- 12.08, N = 9 SE +/- 29.35, N = 9 1169.15 1783.19 1. (F9X) gfortran options: -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein 2 x Xeon Platinum 8380 Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.33, N = 15 SE +/- 0.23, N = 15 31.56 20.84 1. (CXX) g++ options: -O3 -pthread -lm
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl 2 x Xeon Platinum 8380 Xeon Platinum 8380 500 1000 1500 2000 2500 SE +/- 4.10, N = 3 SE +/- 0.67, N = 3 2191 1452 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 5K 10K 15K 20K 25K SE +/- 396.15, N = 8 SE +/- 195.78, N = 5 24810.2 16445.2 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.10.20 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.24, N = 5 SE +/- 0.41, N = 3 21.63 32.01
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 3 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.04, N = 4 SE +/- 0.01, N = 3 15.51 22.87 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.2851 0.5702 0.8553 1.1404 1.4255 SE +/- 0.010254, N = 9 SE +/- 0.006531, N = 15 1.267000 0.872017 MIN: 0.86 MIN: 0.77 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 2 x Xeon Platinum 8380 Xeon Platinum 8380 170K 340K 510K 680K 850K SE +/- 5876.97, N = 15 SE +/- 10511.44, N = 3 541996.24 771533.42 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast 2 x Xeon Platinum 8380 Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.19, N = 4 SE +/- 0.02, N = 3 38.71 27.57 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing 2 x Xeon Platinum 8380 Xeon Platinum 8380 2M 4M 6M 8M 10M SE +/- 103809.83, N = 15 SE +/- 63537.44, N = 3 9170260 6676556 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
ONNX Runtime Model: yolov4 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: yolov4 - Device: OpenMP CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 140 280 420 560 700 SE +/- 5.49, N = 3 SE +/- 2.17, N = 3 482 659 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.4 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 16.43 22.32
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 57.40 77.52
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.9071 1.8142 2.7213 3.6284 4.5355 SE +/- 0.00418, N = 4 SE +/- 0.02087, N = 4 2.99485 4.03139 MIN: 2.85 MIN: 3.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles 2 x Xeon Platinum 8380 Xeon Platinum 8380 60 120 180 240 300 SE +/- 0.65, N = 3 SE +/- 0.72, N = 3 190.68 256.63
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 4K 8K 12K 16K 20K SE +/- 158.49, N = 8 SE +/- 155.70, N = 5 18859.8 14169.2 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.2727 0.5454 0.8181 1.0908 1.3635 SE +/- 0.003790, N = 4 SE +/- 0.000855, N = 4 0.914865 1.212030 MIN: 0.85 MIN: 1.16 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D 2 x Xeon Platinum 8380 Xeon Platinum 8380 700 1400 2100 2800 3500 SE +/- 20.88, N = 4 SE +/- 6.51, N = 3 3086.24 2333.56 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.0742 0.1484 0.2226 0.2968 0.371 SE +/- 0.000574, N = 4 SE +/- 0.000427, N = 4 0.249611 0.329636 MIN: 0.23 MIN: 0.29 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.024, N = 8 SE +/- 0.007, N = 7 4.709 6.211 1. (CXX) g++ options: -O2 -lOpenCL
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Summer Nature 4K 2 x Xeon Platinum 8380 Xeon Platinum 8380 120 240 360 480 600 SE +/- 0.65, N = 3 SE +/- 0.60, N = 3 532.57 404.27 MIN: 189.3 / MAX: 586.86 MIN: 275.43 / MAX: 456.48 1. (CC) gcc options: -pthread -lm
MariaDB Clients: 256 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 256 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 1.84, N = 3 SE +/- 1.12, N = 3 697 918 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt
MariaDB Clients: 512 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 512 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 2.75, N = 3 SE +/- 0.76, N = 3 664 870 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.02, N = 4 SE +/- 0.02, N = 4 11.42 14.93 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
KTX-Software toktx Settings: UASTC 3 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.005, N = 8 SE +/- 0.006, N = 7 4.658 6.013
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 3.53, N = 3 820 641 MIN: 1 / MAX: 3230 MIN: 1 / MAX: 2858
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian 2 x Xeon Platinum 8380 Xeon Platinum 8380 160 320 480 640 800 SE +/- 2.03, N = 3 SE +/- 2.33, N = 3 732 586 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small 2 x Xeon Platinum 8380 Xeon Platinum 8380 6K 12K 18K 24K 30K SE +/- 90.91, N = 4 SE +/- 13.81, N = 4 28391.4 23125.0 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 2.14, N = 3 SE +/- 4.02, N = 3 675.16 812.26 MIN: 645.81 MIN: 778.91 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.14, N = 4 SE +/- 0.06, N = 4 11.96 14.37
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 0.92, N = 3 SE +/- 2.62, N = 3 675.12 810.36 MIN: 649.43 MIN: 779.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 13 26 39 52 65 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 48.07 56.58
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 6.21 7.30
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 15 30 45 60 75 SE +/- 0.32, N = 3 SE +/- 0.25, N = 3 57.64 67.16
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 18.71 21.79
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 5.94, N = 10 SE +/- 11.50, N = 3 753 867 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
KTX-Software toktx Settings: UASTC 3 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 2 x Xeon Platinum 8380 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.024, N = 5 SE +/- 0.026, N = 5 9.111 10.387
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily 2 x Xeon Platinum 8380 Xeon Platinum 8380 30 60 90 120 150 123.70 140.51
ONNX Runtime Model: bertsquad-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: bertsquad-10 - Device: OpenMP CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 130 260 390 520 650 SE +/- 8.14, N = 12 SE +/- 6.23, N = 5 516 586 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.063, N = 15 SE +/- 0.063, N = 15 7.652 6.762 1. (CXX) g++ options: -O2 -lOpenCL
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast 2 x Xeon Platinum 8380 Xeon Platinum 8380 11 22 33 44 55 SE +/- 0.33, N = 4 SE +/- 0.08, N = 4 47.84 42.65 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.4547 0.9094 1.3641 1.8188 2.2735 SE +/- 0.00217, N = 5 SE +/- 0.00210, N = 5 1.81271 2.02106 MIN: 1.67 MIN: 1.69 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 2.33, N = 3 1042 1159 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Chimera 1080p 10-bit 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 1.95, N = 3 SE +/- 0.41, N = 3 861.39 775.38 MIN: 524.86 / MAX: 1144.29 MIN: 588.21 / MAX: 1071.6 1. (CC) gcc options: -pthread -lm
Tungsten Renderer Scene: Non-Exponential OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.6328 1.2656 1.8984 2.5312 3.164 SE +/- 0.01197, N = 10 SE +/- 0.00595, N = 10 2.56596 2.81248 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile 2 x Xeon Platinum 8380 Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 439.19, N = 3 SE +/- 82.87, N = 3 74702.4 81669.1
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K 2 x Xeon Platinum 8380 Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 28.65 31.23 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 100 200 300 400 500 SE +/- 1.03, N = 3 SE +/- 1.28, N = 3 439.37 476.02 MIN: 423.06 MIN: 462.14 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 100 200 300 400 500 SE +/- 2.02, N = 3 SE +/- 0.97, N = 3 439.64 476.21 MIN: 422.12 MIN: 462.69 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.4.2 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 35.34 38.27
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 70 140 210 280 350 SE +/- 2.91, N = 15 SE +/- 0.54, N = 10 313.93 290.36 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 100 200 300 400 500 SE +/- 2.16, N = 3 SE +/- 1.74, N = 3 441.26 475.86 MIN: 423.47 MIN: 461.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
ONNX Runtime Model: shufflenet-v2-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: shufflenet-v2-10 - Device: OpenMP CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 2K 4K 6K 8K 10K SE +/- 2.92, N = 3 SE +/- 18.20, N = 3 8402 9056 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 8 16 24 32 40 SE +/- 0.33, N = 3 SE +/- 0.21, N = 3 33.43 31.06
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 10 20 30 40 50 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 39.84 42.71
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding 2 x Xeon Platinum 8380 Xeon Platinum 8380 1100 2200 3300 4400 5500 SE +/- 46.19, N = 3 SE +/- 4.90, N = 3 4997.05 5305.67 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.0819 0.1638 0.2457 0.3276 0.4095 SE +/- 0.001200, N = 3 SE +/- 0.000930, N = 3 0.363977 0.343258 MIN: 0.32 MIN: 0.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.3284 0.6568 0.9852 1.3136 1.642 SE +/- 0.00305, N = 7 SE +/- 0.00041, N = 7 1.39717 1.45952 MIN: 1.24 MIN: 1.43 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.3211 0.6422 0.9633 1.2844 1.6055 SE +/- 0.00190, N = 5 SE +/- 0.00142, N = 5 1.36768 1.42703 MIN: 1.33 MIN: 1.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.31, N = 3 SE +/- 0.12, N = 3 38.51 36.97
ONNX Runtime Model: fcn-resnet101-11 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: fcn-resnet101-11 - Device: OpenMP CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 40 80 120 160 200 SE +/- 1.69, N = 3 SE +/- 1.48, N = 3 197 204 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 110 220 330 440 550 SE +/- 1.83, N = 10 SE +/- 0.89, N = 11 469.70 485.54 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Tungsten Renderer Scene: Water Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 20.30 20.91 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
WebP2 Image Encode Encode Settings: Quality 100, Lossless Compression OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 100, Lossless Compression 2 x Xeon Platinum 8380 Xeon Platinum 8380 90 180 270 360 450 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 413.22 425.32 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless 2 x Xeon Platinum 8380 Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.31, N = 3 SE +/- 0.18, N = 3 29.69 30.53 1. (CXX) g++ options: -O3 -fPIC -lm
WebP2 Image Encode Encode Settings: Quality 95, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 95, Compression Effort 7 2 x Xeon Platinum 8380 Xeon Platinum 8380 50 100 150 200 250 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 218.16 223.97 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
WebP2 Image Encode Encode Settings: Quality 75, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 75, Compression Effort 7 2 x Xeon Platinum 8380 Xeon Platinum 8380 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 117.57 120.69 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.0527 0.1054 0.1581 0.2108 0.2635 SE +/- 0.001610, N = 4 SE +/- 0.000310, N = 4 0.228632 0.234327 MIN: 0.2 MIN: 0.21 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 0.0987 0.1974 0.2961 0.3948 0.4935 SE +/- 0.001219, N = 5 SE +/- 0.000558, N = 5 0.438511 0.427987 MIN: 0.4 MIN: 0.41 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
ASKAP Test: Hogbom Clean OpenMP OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP 2 x Xeon Platinum 8380 Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 11.55, N = 4 SE +/- 14.64, N = 4 1238.71 1266.33 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 100 200 300 400 500 SE +/- 5.22, N = 15 SE +/- 4.09, N = 15 475.45 485.12 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 2 x Xeon Platinum 8380 Xeon Platinum 8380 40M 80M 120M 160M 200M SE +/- 1334158.46, N = 15 SE +/- 953041.14, N = 3 178965233 175890300 1. (CXX) g++ options: -O3 -fopenmp
WebP2 Image Encode Encode Settings: Quality 100, Compression Effort 5 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 100, Compression Effort 5 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.007, N = 6 SE +/- 0.002, N = 6 6.251 6.303 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 80 160 240 320 400 SE +/- 2.30, N = 9 SE +/- 2.16, N = 10 371.88 370.64 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p 2 x Xeon Platinum 8380 Xeon Platinum 8380 130 260 390 520 650 SE +/- 3.29, N = 11 SE +/- 1.28, N = 12 584.72 583.64 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenVKL Benchmark: vklBenchmarkVdbVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkVdbVolume 2 x Xeon Platinum 8380 Xeon Platinum 8380 6M 12M 18M 24M 30M SE +/- 89609.36, N = 3 SE +/- 65507.38, N = 3 29143044 29092155 MIN: 1069452 / MAX: 176387184 MIN: 1047483 / MAX: 175929480
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync 2 x Xeon Platinum 8380 Xeon Platinum 8380 100K 200K 300K 400K 500K SE +/- 556.11, N = 3 SE +/- 985.63, N = 3 482191 481504 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping 2 x Xeon Platinum 8380 Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 13.05, N = 3 SE +/- 3.16, N = 3 1354.59 1356.01 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenVKL Benchmark: vklBenchmarkStructuredVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkStructuredVolume 2 x Xeon Platinum 8380 Xeon Platinum 8380 20M 40M 60M 80M 100M SE +/- 177762.64, N = 3 SE +/- 47834.23, N = 3 104922070 105023963 MIN: 1391949 / MAX: 891929412 MIN: 1379843 / MAX: 899785764
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 37.69 37.68 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile 2 x Xeon Platinum 8380 Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 19.79 19.79
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Exhaustive Xeon Platinum 8380 rest 5 10 15 20 25 SE +/- 0.02, N = 3 19.60 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Thorough Xeon Platinum 8380 rest 2 4 6 8 10 SE +/- 0.0247, N = 3 7.4107 1. (CXX) g++ options: -O3 -flto -pthread
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Medium Xeon Platinum 8380 rest 1.0915 2.183 3.2745 4.366 5.4575 SE +/- 0.0185, N = 3 4.8512 1. (CXX) g++ options: -O3 -flto -pthread
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 1080p Xeon Platinum 8380 rest 6 12 18 24 30 SE +/- 0.02, N = 3 25.46 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 1080p Xeon Platinum 8380 rest 3 6 9 12 15 SE +/- 0.01, N = 3 11.80 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K Xeon Platinum 8380 rest 4 8 12 16 20 SE +/- 0.07, N = 3 13.97 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Xeon Platinum 8380 rest 1.2758 2.5516 3.8274 5.1032 6.379 SE +/- 0.00, N = 3 5.67 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Xeon Platinum 8380 rest 20 40 60 80 100 SE +/- 0.06, N = 3 95.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Xeon Platinum 8380 rest 30 60 90 120 150 SE +/- 0.12, N = 3 132.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 rest 16 32 48 64 80 SE +/- 0.21, N = 3 71.4 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 rest 20 40 60 80 100 SE +/- 0.52, N = 3 98.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8380 rest 50 100 150 200 250 SE +/- 0.49, N = 3 207.5 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8380 rest 70 140 210 280 350 SE +/- 1.16, N = 3 306.8 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8380 rest 30 60 90 120 150 SE +/- 0.60, N = 3 129.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8380 rest 70 140 210 280 350 SE +/- 0.12, N = 3 305.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8380 rest 40 80 120 160 200 SE +/- 0.03, N = 3 174.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8380 rest 60 120 180 240 300 SE +/- 0.45, N = 3 273.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8380 rest 20 40 60 80 100 SE +/- 2.67, N = 3 110.1 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8380 rest 60 120 180 240 300 SE +/- 0.25, N = 3 279.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test Xeon Platinum 8380 rest 30M 60M 90M 120M 150M SE +/- 305505.05, N = 3 120400000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
ONNX Runtime Model: super-resolution-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: super-resolution-10 - Device: OpenMP CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 1600 3200 4800 6400 8000 SE +/- 15.90, N = 3 SE +/- 184.76, N = 12 7609 6381 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: LBC, LBRY Credits 2 x Xeon Platinum 8380 Xeon Platinum 8380 90K 180K 270K 360K 450K SE +/- 30611.01, N = 12 SE +/- 7613.62, N = 12 402726 273780 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Myriad-Groestl 2 x Xeon Platinum 8380 Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 1515.66, N = 15 SE +/- 5943.89, N = 15 84872 75707 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Skeincoin 2 x Xeon Platinum 8380 Xeon Platinum 8380 170K 340K 510K 680K 850K SE +/- 19372.86, N = 12 SE +/- 23435.25, N = 12 774163 407502 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Blake-2 S 2 x Xeon Platinum 8380 Xeon Platinum 8380 800K 1600K 2400K 3200K 4000K SE +/- 58124.19, N = 12 SE +/- 117578.84, N = 12 3662348 2476303 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Deepcoin 2 x Xeon Platinum 8380 Xeon Platinum 8380 16K 32K 48K 64K 80K SE +/- 2190.61, N = 15 SE +/- 1301.01, N = 15 75061 33583 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: x25x 2 x Xeon Platinum 8380 Xeon Platinum 8380 600 1200 1800 2400 3000 SE +/- 50.45, N = 15 SE +/- 14.01, N = 3 2725.03 1022.32 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 68.99, N = 15 SE +/- 2.97, N = 3 757.06 813.03 MIN: 648.2 MIN: 779.61 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.01372, N = 3 SE +/- 0.21071, N = 12 6.96910 4.51612 MIN: 6.54 MIN: 3.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene 2 x Xeon Platinum 8380 Xeon Platinum 8380 20 40 60 80 100 SE +/- 2.28, N = 15 SE +/- 1.05, N = 3 81.51 74.90 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.63, N = 15 SE +/- 0.27, N = 15 14.11 14.39 MIN: 10.63 / MAX: 19.45 MIN: 12.31 / MAX: 19.48
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: CPU 2 x Xeon Platinum 8380 Xeon Platinum 8380 2 4 6 8 10 SE +/- 0.14, N = 15 SE +/- 0.06, N = 15 6.89 4.50 MIN: 2.38 / MAX: 8.45 MIN: 1.72 / MAX: 5.53
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte 2 x Xeon Platinum 8380 Xeon Platinum 8380 11 22 33 44 55 SE +/- 0.66, N = 3 SE +/- 0.81, N = 15 47.44 44.02 1. (CXX) g++ options: -O2 -lOpenCL
Phoronix Test Suite v10.8.4