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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2106033-IB-SINGLE68975
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 3 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 4 Tests
Chess Test Suite 3 Tests
Timed Code Compilation 12 Tests
C/C++ Compiler Tests 26 Tests
CPU Massive 35 Tests
Creator Workloads 30 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 5 Tests
Database Test Suite 3 Tests
Encoding 8 Tests
Fortran Tests 7 Tests
Game Development 7 Tests
HPC - High Performance Computing 23 Tests
Imaging 3 Tests
Common Kernel Benchmarks 2 Tests
LAPACK (Linear Algebra Pack) Tests 3 Tests
Linear Algebra 2 Tests
Machine Learning 4 Tests
Molecular Dynamics 10 Tests
MPI Benchmarks 7 Tests
Multi-Core 55 Tests
NVIDIA GPU Compute 6 Tests
Intel oneAPI 5 Tests
OpenMPI Tests 16 Tests
Programmer / Developer System Benchmarks 14 Tests
Python Tests 8 Tests
Raytracing 5 Tests
Renderers 11 Tests
Scientific Computing 14 Tests
Software Defined Radio 2 Tests
Server 5 Tests
Server CPU Tests 24 Tests
Texture Compression 3 Tests
Video Encoding 8 Tests
Common Workstation Benchmarks 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x Xeon Platinum 8380
June 01 2021
  18 Hours, 29 Minutes
Xeon Platinum 8380
June 02 2021
  21 Hours, 58 Minutes
Xeon Platinum 8380 rest
June 03 2021
  51 Minutes
Invert Hiding All Results Option
  13 Hours, 46 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


server-cpus-june-2021 ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen Resolution2 x Xeon Platinum 8380Xeon Platinum 8380Xeon Platinum 8380 rest2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 0998504GB7682GB INTEL SSDPF2KX076TZllvmpipeVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPUbuntu 21.045.13.0-051300rc4-generic (x86_64) 20210530GNOME Shell 3.38.4X Server4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits)GCC 10.3.0ext41920x1080Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads)252GBASPEEDOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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: 0xd000270Python Details- 2 x Xeon Platinum 8380, Xeon Platinum 8380: Python 3.9.5Security 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 Metriccpuminer-opt: Magicpuminer-opt: Garlicoinsvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 4Knpb: SP.Bnpb: SP.Cpennant: leblancbigincompact3d: input.i3d 193 Cells Per Directionopenfoam: Motorbike 60Mnpb: MG.Cliquid-dsp: 128 - 256 - 57rocksdb: Rand Readopenssl: RSA 4096-bit Performanceincompact3d: input.i3d 129 Cells Per Directionaircrack-ng: blender: Classroom - CPU-Onlyhelsing: 14 digitaskap: tConvolve MPI - Degriddingc-ray: Total Time - 4K, 16 Rays Per Pixeltachyon: Total Timejohn-the-ripper: Blowfishembree: Pathtracer - Asian Dragoncoremark: CoreMark Size 666 - Iterations Per Secondrelion: Basic - CPUm-queens: Time To Solveliquid-dsp: 160 - 256 - 57askap: tConvolve MPI - Griddingastcenc: Exhaustivetoybrot: TBBprimesieve: 1e12 Prime Number Generationnpb: EP.Dtoybrot: OpenMPonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUjohn-the-ripper: MD5toybrot: C++ Threadsamg: asmfish: 1024 Hash Memory, 26 Depthnpb: LU.Cnamd: ATPase Simulation - 327,506 Atomsmt-dgemm: Sustained Floating-Point Ratestockfish: Total Timeincompact3d: X3D-benchmarking input.i3dlulesh: blender: Barbershop - CPU-Onlyv-ray: CPUrays1bench: Large Sceneblender: Pabellon Barcelona - CPU-Onlywrf: conus 2.5kmtoktx: UASTC 4 + Zstd Compression 19embree: Pathtracer ISPC - Asian Dragonrodinia: OpenMP LavaMDliquid-dsp: 64 - 256 - 57npb: EP.Cxmrig: Wownero - 1Mgraphics-magick: Sharpenembree: Pathtracer - Asian Dragon Objxmrig: Monero - 1Mblender: BMW27 - CPU-Onlygromacs: MPI CPU - water_GMX50_bareembree: Pathtracer - Crowntensorflow-lite: Inception ResNet V2embree: Pathtracer ISPC - Asian Dragon Objtensorflow-lite: Inception V4compress-7zip: Compress Speed Testnpb: FT.Cnpb: CG.Cgraphics-magick: Enhancedtoybrot: C++ Tasksaskap: tConvolve MT - Degriddingtensorflow-lite: Mobilenet Floatluxcorerender: DLSC - CPUembree: Pathtracer ISPC - Crownoidn: RTLightmap.hdr.4096x4096npb: BT.Ctensorflow-lite: Mobilenet Quanttensorflow-lite: SqueezeNetblender: Fishy Cat - CPU-Onlypovray: Trace Timeebizzy: appleseed: Material Testeroidn: RT.hdr_alb_nrm.3840x2160nwchem: C240 Buckyballoidn: RT.ldr_alb_nrm.3840x2160pennant: sedovbigonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUopenfoam: Motorbike 30Monednn: Deconvolution Batch shapes_3d - f32 - CPUbuild-llvm: Ninjaonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUluxcorerender: Orange Juice - CPUtungsten: Haironednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUlammps: 20k Atomssvt-hevc: 1 - Bosphorus 1080pcloverleaf: Lagrangian-Eulerian Hydrodynamicsluxcorerender: Danish Mood - CPUbuild-nodejs: Time To Compileqe: AUSURF112lammps: Rhodopsin Proteingraphics-magick: Swirlaskap: tConvolve OpenMP - Degriddingbuild-linux-kernel: Time To Compilebasis: UASTC Level 3onednn: IP Shapes 1D - u8s8f32 - CPUkeydb: kvazaar: Bosphorus 4K - Very Fastrocksdb: Read While Writingonnx: yolov4 - OpenMP CPUbuild-ffmpeg: Time To Compileappleseed: Disney Materialonednn: IP Shapes 1D - bf16bf16bf16 - CPUbuild-llvm: Unix Makefilesaskap: tConvolve OpenMP - Griddingonednn: IP Shapes 1D - f32 - CPUnpb: IS.Donednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUrodinia: OpenMP CFD Solverdav1d: Summer Nature 4Kmysqlslap: 256mysqlslap: 512basis: UASTC Level 2toktx: UASTC 3openvkl: vklBenchmarkgraphics-magick: Noise-Gaussianminife: Smallonednn: Recurrent Neural Network Training - f32 - CPUbuild-imagemagick: Time To Compileonednn: Recurrent Neural Network Training - u8s8f32 - CPUbuild-godot: Time To Compileplaidml: No - Inference - ResNet 50 - CPUbuild2: Time To Compilebuild-mesa: Time To Compilegraphics-magick: Rotatetoktx: UASTC 3 + Zstd Compression 19appleseed: Emilyonnx: bertsquad-10 - OpenMP CPUrodinia: OpenMP Streamclusterkvazaar: Bosphorus 4K - Ultra Fastonednn: IP Shapes 3D - bf16bf16bf16 - CPUgraphics-magick: HWB Color Spacedav1d: Chimera 1080p 10-bittungsten: Non-Exponentialtensorflow-lite: NASNet Mobilex265: Bosphorus 4Konednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUbuild-php: Time To Compilesvt-hevc: 7 - Bosphorus 1080ponednn: Recurrent Neural Network Inference - u8s8f32 - CPUonnx: shufflenet-v2-10 - OpenMP CPUplaidml: No - Inference - VGG19 - CPUbuild-gdb: Time To Compileaskap: tConvolve MT - Griddingonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: IP Shapes 3D - f32 - CPUplaidml: No - Inference - VGG16 - CPUonnx: fcn-resnet101-11 - OpenMP CPUsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080ptungsten: Water Causticwebp2: Quality 100, Lossless Compressionavifenc: 6, Losslesswebp2: Quality 95, Compression Effort 7webp2: Quality 75, Compression Effort 7onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUaskap: Hogbom Clean OpenMPsvt-vp9: VMAF Optimized - Bosphorus 1080pkripke: webp2: Quality 100, Compression Effort 5svt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080popenvkl: vklBenchmarkVdbVolumerocksdb: Rand Fill Syncttsiod-renderer: Phong Rendering With Soft-Shadow Mappingopenvkl: vklBenchmarkStructuredVolumebuild-wasmer: Time To Compilebuild-apache: Time To Compileastcenc: Exhaustiveastcenc: Thoroughastcenc: Mediumvpxenc: Speed 5 - Bosphorus 1080pvpxenc: Speed 0 - Bosphorus 1080pvpxenc: Speed 5 - Bosphorus 4Kvpxenc: Speed 0 - Bosphorus 4Ksrsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAMsrsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAMsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMsrsran: OFDM_Testonnx: super-resolution-10 - OpenMP CPUcpuminer-opt: LBC, LBRY Creditscpuminer-opt: Myriad-Groestlcpuminer-opt: Skeincoincpuminer-opt: Blake-2 Scpuminer-opt: Deepcoincpuminer-opt: x25xonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUyafaray: Total Time For Sample Sceneluxcorerender: Rainbow Colors and Prism - CPUluxcorerender: LuxCore Benchmark - CPUrodinia: OpenMP Leukocyte2 x Xeon Platinum 8380Xeon Platinum 8380Xeon Platinum 8380 rest24115873651.804126957.4164.734123538.1492499.874.70761011.0581346103.61118831.52327926666737383196617835.82.57966831211019.99071.1181.46418222.511.00813.682511886983.57232365407.624214350.74311.301308653333320662.016.642169243.6938890.3472812.089241020000069922082103333171121628188790.140.2706428.146733180945380291.41619935311.845103.8766328346.3187.639822.72754.917107.902539.06930473333337939.0242770.867272.451726504.228.249.06364.770957275089.6186666967355140100812.5440188.841125788312928.832738.99.4175.49671.44198052.3834155.047974.644.459.2572035986177.7799162.981846.82.9914.413793.259123.5639614.300.839556127.9930.1906280.91508614.335.733310.60437835.98937.4910.086.9790.5701169.1531.561219124810.221.62715.5131.26700541996.2438.71917026048216.42657.3969832.99485190.68318859.80.9148653086.240.2496114.709532.5769766411.4154.65882073228391.4675.16311.962675.11548.0686.2157.63918.7127539.111123.7005295167.65247.841.812711042861.392.5659674702.428.65439.372439.64035.344313.93441.260840233.4339.8354997.050.3639771.397171.3676838.51197469.7020.3009413.22329.692218.163117.5730.2286320.4385111238.71475.451789652336.251371.88584.72291430444821911354.5910492207037.68819.7907609402726848727741633662348750612725.03757.0626.9691081.51314.116.8947.4434233241346.631561821.8011.85950133.5837645.4111.3289924.0432320224.5856287.5315652666671821809618726.85.26849863105477.352142.20161.6479239.5921.64526.87366055342.61001206142.696836686.96122.128157930000010580.932.4903134867.1664593.84140574.0268053056671343910844116678922038498453.550.5188914.69613894879448554.93876118779.645195.1635347184.56164.0118356.463102.03058.291971.99116540666674334.3323539.937039.993414658.251.055.01736.0739102606050.0994117846320159657275.0822890.25641137267452.0756410.05.5044.16890.85117333.4757591.080455.774.5115.5151215587106.172711.783085.11.7923.843005.376525.8743323.491.37155208.6510.3103621.482568.959.154460.96017422.68223.7015.924.42142.5091783.1920.841145216445.232.01222.8700.872017771533.4227.57667655665922.31677.5219254.03139256.63014169.21.212032333.560.3296366.211404.2791887014.9306.01364158623125.0812.26014.369810.35856.5807.3067.16121.79486710.387140.5090895866.76242.652.021061159775.382.8124881669.131.23476.024476.21438.269290.36475.861905631.0642.7105305.670.3432581.459521.4270336.97204485.5420.9080425.32430.533223.969120.6900.2343270.4279871266.33485.121758903006.303370.64583.64290921554815041356.0110502396337.68319.7886381273780757074075022476303335831022.32813.0254.5161274.90314.394.5044.02119.59597.41074.851225.4611.8013.975.6795.9132.271.498.3207.5306.8129.6305.6174.3273.2110.1279.9120400000OpenBenchmarking.org

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.2VGR Performance Metric2 x Xeon Platinum 8380Xeon Platinum 8380500K1000K1500K2000K2500K24115874233241. (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

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Magi2 x Xeon Platinum 8380Xeon Platinum 83808001600240032004000SE +/- 39.37, N = 15SE +/- 12.34, N = 153651.801346.631. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Magi2 x Xeon Platinum 8380Xeon Platinum 83806001200180024003000Min: 3211.65 / Avg: 3651.8 / Max: 3805.3Min: 1307.01 / Avg: 1346.63 / Max: 1449.631. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Garlicoin2 x Xeon Platinum 8380Xeon Platinum 83809K18K27K36K45KSE +/- 585.01, N = 15SE +/- 181.40, N = 441269156181. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Garlicoin2 x Xeon Platinum 8380Xeon Platinum 83807K14K21K28K35KMin: 34490 / Avg: 41268.67 / Max: 43860Min: 15160 / Avg: 15617.5 / Max: 160201. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 83801326395265SE +/- 0.11, N = 4SE +/- 0.05, N = 357.4221.801. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 83801122334455Min: 57.12 / Avg: 57.42 / Max: 57.61Min: 21.7 / Avg: 21.8 / Max: 21.861. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 83801.06522.13043.19564.26085.326SE +/- 0.036, N = 3SE +/- 0.007, N = 34.7341.8591. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 4.67 / Avg: 4.73 / Max: 4.8Min: 1.85 / Avg: 1.86 / Max: 1.871. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B2 x Xeon Platinum 8380Xeon Platinum 838030K60K90K120K150KSE +/- 276.83, N = 9SE +/- 122.82, N = 6123538.1450133.581. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KMin: 122516.28 / Avg: 123538.14 / Max: 124751.69Min: 49878.03 / Avg: 50133.58 / Max: 507101. (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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.C2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KSE +/- 74.38, N = 4SE +/- 75.47, N = 392499.8737645.411. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.C2 x Xeon Platinum 8380Xeon Platinum 838016K32K48K64K80KMin: 92296.12 / Avg: 92499.87 / Max: 92623.78Min: 37495.49 / Avg: 37645.41 / Max: 37735.551. (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

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbig2 x Xeon Platinum 8380Xeon Platinum 83803691215SE +/- 0.011962, N = 7SE +/- 0.018568, N = 44.70761011.3289901. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbig2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 4.66 / Avg: 4.71 / Max: 4.74Min: 11.28 / Avg: 11.33 / Max: 11.371. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction2 x Xeon Platinum 8380Xeon Platinum 8380612182430SE +/- 0.02, N = 4SE +/- 0.01, N = 311.0624.041. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction2 x Xeon Platinum 8380Xeon Platinum 8380612182430Min: 11.02 / Avg: 11.06 / Max: 11.09Min: 24.03 / Avg: 24.04 / Max: 24.061. (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

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60M2 x Xeon Platinum 8380Xeon Platinum 838050100150200250SE +/- 0.05, N = 3SE +/- 0.13, N = 3103.61224.581. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60M2 x Xeon Platinum 8380Xeon Platinum 83804080120160200Min: 103.52 / Avg: 103.61 / Max: 103.69Min: 224.44 / Avg: 224.58 / Max: 224.831. (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

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C2 x Xeon Platinum 8380Xeon Platinum 838030K60K90K120K150KSE +/- 268.68, N = 11SE +/- 182.12, N = 9118831.5256287.531. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KMin: 117326.18 / Avg: 118831.52 / Max: 119978.83Min: 55378.33 / Avg: 56287.53 / Max: 56977.91. (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

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380700M1400M2100M2800M3500MSE +/- 4603018.33, N = 3SE +/- 3090487.20, N = 3327926666715652666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380600M1200M1800M2400M3000MMin: 3273700000 / Avg: 3279266666.67 / Max: 3288400000Min: 1560800000 / Avg: 1565266666.67 / Max: 15712000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Read2 x Xeon Platinum 8380Xeon Platinum 838080M160M240M320M400MSE +/- 1003430.17, N = 3SE +/- 1359270.00, N = 33738319661821809611. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Read2 x Xeon Platinum 8380Xeon Platinum 838060M120M180M240M300MMin: 372599347 / Avg: 373831966 / Max: 375819809Min: 179565210 / Avg: 182180961.33 / Max: 1841301081. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KSE +/- 75.18, N = 3SE +/- 55.43, N = 317835.88726.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KMin: 17710.1 / Avg: 17835.83 / Max: 17970.1Min: 8669.3 / Avg: 8726.77 / Max: 8837.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction2 x Xeon Platinum 8380Xeon Platinum 83801.18542.37083.55624.74165.927SE +/- 0.00858289, N = 9SE +/- 0.00960015, N = 72.579668315.268498631. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.54 / Avg: 2.58 / Max: 2.64Min: 5.24 / Avg: 5.27 / Max: 5.31. (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

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.22 x Xeon Platinum 8380Xeon Platinum 838050K100K150K200K250KSE +/- 353.02, N = 3SE +/- 128.50, N = 3211019.99105477.351. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.22 x Xeon Platinum 8380Xeon Platinum 838040K80K120K160K200KMin: 210319.34 / Avg: 211019.99 / Max: 211445.78Min: 105232.53 / Avg: 105477.35 / Max: 105667.471. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 8380306090120150SE +/- 0.11, N = 3SE +/- 0.25, N = 371.11142.20
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 8380306090120150Min: 70.95 / Avg: 71.11 / Max: 71.31Min: 141.94 / Avg: 142.2 / Max: 142.7

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digit2 x Xeon Platinum 8380Xeon Platinum 83804080120160200SE +/- 0.89, N = 3SE +/- 0.57, N = 381.46161.651. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digit2 x Xeon Platinum 8380Xeon Platinum 8380306090120150Min: 79.97 / Avg: 81.46 / Max: 83.05Min: 160.64 / Avg: 161.65 / Max: 162.611. (CC) gcc options: -O2 -pthread

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Degridding2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KSE +/- 73.04, N = 3SE +/- 37.57, N = 318222.509239.591. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Degridding2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KMin: 18096.3 / Avg: 18222.5 / Max: 18349.3Min: 9174.67 / Avg: 9239.59 / Max: 9304.811. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.01, N = 5SE +/- 0.17, N = 311.0121.651. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 10.98 / Avg: 11.01 / Max: 11.04Min: 21.31 / Avg: 21.64 / Max: 21.821. (CC) gcc options: -lm -lpthread -O3

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total Time2 x Xeon Platinum 8380Xeon Platinum 8380612182430SE +/- 0.05, N = 4SE +/- 0.07, N = 313.6826.871. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total Time2 x Xeon Platinum 8380Xeon Platinum 8380612182430Min: 13.62 / Avg: 13.68 / Max: 13.83Min: 26.73 / Avg: 26.87 / Max: 26.961. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish2 x Xeon Platinum 8380Xeon Platinum 838030K60K90K120K150KSE +/- 139.20, N = 3SE +/- 132.64, N = 3118869605531. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KMin: 118616 / Avg: 118869.33 / Max: 119096Min: 60288 / Avg: 60553 / Max: 606961. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.22, N = 5SE +/- 0.50, N = 483.5742.61MIN: 69.17 / MAX: 92.21MIN: 39.84 / MAX: 49.36
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon2 x Xeon Platinum 8380Xeon Platinum 83801632486480Min: 83.06 / Avg: 83.57 / Max: 84.37Min: 41.71 / Avg: 42.61 / Max: 43.71

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second2 x Xeon Platinum 8380Xeon Platinum 8380500K1000K1500K2000K2500KSE +/- 1412.48, N = 3SE +/- 1975.05, N = 32365407.621206142.701. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second2 x Xeon Platinum 8380Xeon Platinum 8380400K800K1200K1600K2000KMin: 2363542.36 / Avg: 2365407.62 / Max: 2368177.61Min: 1202194 / Avg: 1206142.7 / Max: 1208208.261. (CC) gcc options: -O2 -lrt" -lrt

RELION

RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380150300450600750SE +/- 1.68, N = 3SE +/- 1.68, N = 3350.74686.961. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380120240360480600Min: 349.05 / Avg: 350.74 / Max: 354.1Min: 684.5 / Avg: 686.96 / Max: 690.161. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -lmpi

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.03, N = 5SE +/- 0.04, N = 311.3022.131. (CXX) g++ options: -fopenmp -O2 -march=native
OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 11.22 / Avg: 11.3 / Max: 11.38Min: 22.06 / Avg: 22.13 / Max: 22.21. (CXX) g++ options: -fopenmp -O2 -march=native

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 160 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380700M1400M2100M2800M3500MSE +/- 284800.12, N = 3SE +/- 2451530.13, N = 3308653333315793000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 160 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380500M1000M1500M2000M2500MMin: 3086200000 / Avg: 3086533333.33 / Max: 3087100000Min: 1574400000 / Avg: 1579300000 / Max: 15819000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Gridding2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KSE +/- 93.94, N = 3SE +/- 49.28, N = 320662.010580.91. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - Gridding2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KMin: 20499.7 / Avg: 20661.97 / Max: 20825.1Min: 10495.8 / Avg: 10580.93 / Max: 10666.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive2 x Xeon Platinum 8380Xeon Platinum 8380816243240SE +/- 0.01, N = 3SE +/- 0.05, N = 316.6432.491. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 16.63 / Avg: 16.64 / Max: 16.66Min: 32.4 / Avg: 32.49 / Max: 32.591. (CXX) g++ options: -O3 -flto -pthread

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBB2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KSE +/- 55.68, N = 9SE +/- 115.12, N = 86924134861. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBB2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KMin: 6620 / Avg: 6923.89 / Max: 7234Min: 13151 / Avg: 13486.25 / Max: 141221. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generation2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.010, N = 9SE +/- 0.020, N = 63.6937.1661. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generation2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 3.64 / Avg: 3.69 / Max: 3.73Min: 7.09 / Avg: 7.17 / Max: 7.221. (CXX) g++ options: -O3 -lpthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KSE +/- 95.83, N = 5SE +/- 12.97, N = 38890.344593.841. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D2 x Xeon Platinum 8380Xeon Platinum 838015003000450060007500Min: 8529.39 / Avg: 8890.34 / Max: 9056.45Min: 4568.5 / Avg: 4593.84 / Max: 4611.331. (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

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMP2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KSE +/- 8.35, N = 6SE +/- 13.75, N = 47281140571. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMP2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KMin: 7250 / Avg: 7280.5 / Max: 7301Min: 14039 / Avg: 14057 / Max: 140981. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.9061.8122.7183.6244.53SE +/- 0.00172, N = 7SE +/- 0.00912, N = 72.089244.02680MIN: 2.03MIN: 3.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.08 / Avg: 2.09 / Max: 2.09Min: 4.01 / Avg: 4.03 / Max: 4.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD52 x Xeon Platinum 8380Xeon Platinum 83802M4M6M8M10MSE +/- 14502.87, N = 3SE +/- 15762.12, N = 31020000053056671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD52 x Xeon Platinum 8380Xeon Platinum 83802M4M6M8M10MMin: 10185000 / Avg: 10200000 / Max: 10229000Min: 5287000 / Avg: 5305666.67 / Max: 53370001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threads2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KSE +/- 17.11, N = 6SE +/- 27.98, N = 46992134391. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threads2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KMin: 6939 / Avg: 6992.17 / Max: 7050Min: 13377 / Avg: 13438.75 / Max: 135091. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.22 x Xeon Platinum 8380Xeon Platinum 8380400M800M1200M1600M2000MSE +/- 1152755.01, N = 3SE +/- 408650.35, N = 3208210333310844116671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.22 x Xeon Platinum 8380Xeon Platinum 8380400M800M1200M1600M2000MMin: 2080897000 / Avg: 2082103333.33 / Max: 2084408000Min: 1083601000 / Avg: 1084411666.67 / Max: 10849070001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth2 x Xeon Platinum 8380Xeon Platinum 838040M80M120M160M200MSE +/- 1594885.41, N = 12SE +/- 767934.53, N = 317112162889220384
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth2 x Xeon Platinum 8380Xeon Platinum 838030M60M90M120M150MMin: 166326779 / Avg: 171121627.58 / Max: 182137078Min: 87725441 / Avg: 89220384.33 / Max: 90272862

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C2 x Xeon Platinum 8380Xeon Platinum 838040K80K120K160K200KSE +/- 58.73, N = 4SE +/- 47.08, N = 3188790.1498453.551. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C2 x Xeon Platinum 8380Xeon Platinum 838030K60K90K120K150KMin: 188681.84 / Avg: 188790.14 / Max: 188925.83Min: 98396.26 / Avg: 98453.55 / Max: 98546.91. (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

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms2 x Xeon Platinum 8380Xeon Platinum 83800.11680.23360.35040.46720.584SE +/- 0.00027, N = 3SE +/- 0.00101, N = 30.270640.51889
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 0.27 / Avg: 0.27 / Max: 0.27Min: 0.52 / Avg: 0.52 / Max: 0.52

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rate2 x Xeon Platinum 8380Xeon Platinum 8380714212835SE +/- 0.08, N = 6SE +/- 0.03, N = 428.1514.701. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rate2 x Xeon Platinum 8380Xeon Platinum 8380612182430Min: 27.93 / Avg: 28.15 / Max: 28.44Min: 14.62 / Avg: 14.7 / Max: 14.781. (CC) gcc options: -O3 -march=native -fopenmp

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time2 x Xeon Platinum 8380Xeon Platinum 838040M80M120M160M200MSE +/- 1599896.72, N = 3SE +/- 570049.11, N = 3180945380948794481. (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
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time2 x Xeon Platinum 8380Xeon Platinum 838030M60M90M120M150MMin: 177771047 / Avg: 180945380.33 / Max: 182881423Min: 93759974 / Avg: 94879448.33 / Max: 956261371. (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

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3d2 x Xeon Platinum 8380Xeon Platinum 8380120240360480600SE +/- 1.61, N = 3SE +/- 0.44, N = 3291.42554.941. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3d2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500Min: 289.27 / Avg: 291.42 / Max: 294.57Min: 554.07 / Avg: 554.94 / Max: 555.491. (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

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.32 x Xeon Platinum 8380Xeon Platinum 83808K16K24K32K40KSE +/- 62.90, N = 4SE +/- 16.09, N = 535311.8518779.651. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.32 x Xeon Platinum 8380Xeon Platinum 83806K12K18K24K30KMin: 35149.62 / Avg: 35311.85 / Max: 35445.04Min: 18728.75 / Avg: 18779.64 / Max: 18815.441. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83804080120160200SE +/- 0.05, N = 3SE +/- 0.09, N = 3103.87195.16
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83804080120160200Min: 103.78 / Avg: 103.87 / Max: 103.95Min: 195.03 / Avg: 195.16 / Max: 195.34

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPU2 x Xeon Platinum 8380Xeon Platinum 838014K28K42K56K70KSE +/- 308.74, N = 3SE +/- 131.93, N = 36632835347
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPU2 x Xeon Platinum 8380Xeon Platinum 838011K22K33K44K55KMin: 65816 / Avg: 66328.33 / Max: 66883Min: 35091 / Avg: 35346.67 / Max: 35531

rays1bench

This is a test of rays1bench, a simple path-tracer / ray-tracing that supports SSE and AVX instructions, multi-threading, and other features. This test profile is measuring the performance of the "large scene" in rays1bench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large Scene2 x Xeon Platinum 8380Xeon Platinum 838080160240320400SE +/- 0.57, N = 8SE +/- 0.17, N = 7346.31184.56
OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large Scene2 x Xeon Platinum 8380Xeon Platinum 838060120180240300Min: 344.38 / Avg: 346.31 / Max: 348.5Min: 183.91 / Avg: 184.56 / Max: 185.18

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83804080120160200SE +/- 0.02, N = 3SE +/- 0.11, N = 387.63164.01
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 8380306090120150Min: 87.6 / Avg: 87.63 / Max: 87.66Min: 163.88 / Avg: 164.01 / Max: 164.24

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5km2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20K9822.7318356.461. (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

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 192 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.33, N = 3SE +/- 0.27, N = 354.92102.03
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 192 x Xeon Platinum 8380Xeon Platinum 838020406080100Min: 54.43 / Avg: 54.92 / Max: 55.54Min: 101.52 / Avg: 102.03 / Max: 102.4

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.34, N = 6SE +/- 0.10, N = 5107.9058.29MIN: 96.18 / MAX: 112.26MIN: 53.64 / MAX: 61.72
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon2 x Xeon Platinum 8380Xeon Platinum 838020406080100Min: 106.42 / Avg: 107.9 / Max: 108.68Min: 57.97 / Avg: 58.29 / Max: 58.53

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMD2 x Xeon Platinum 8380Xeon Platinum 83801632486480SE +/- 0.24, N = 3SE +/- 0.66, N = 339.0771.991. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMD2 x Xeon Platinum 8380Xeon Platinum 83801428425670Min: 38.6 / Avg: 39.07 / Max: 39.35Min: 71.16 / Avg: 71.99 / Max: 73.291. (CXX) g++ options: -O2 -lOpenCL

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380700M1400M2100M2800M3500MSE +/- 4053941.84, N = 3SE +/- 1039764.93, N = 3304733333316540666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 572 x Xeon Platinum 8380Xeon Platinum 8380500M1000M1500M2000M2500MMin: 3039300000 / Avg: 3047333333.33 / Max: 3052300000Min: 1652300000 / Avg: 1654066666.67 / Max: 16559000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KSE +/- 69.57, N = 15SE +/- 32.20, N = 117939.024334.331. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C2 x Xeon Platinum 8380Xeon Platinum 838014002800420056007000Min: 7578.26 / Avg: 7939.02 / Max: 8414.84Min: 4117.06 / Avg: 4334.33 / Max: 4467.621. (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

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1M2 x Xeon Platinum 8380Xeon Platinum 83809K18K27K36K45KSE +/- 97.10, N = 3SE +/- 73.93, N = 342770.823539.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1M2 x Xeon Platinum 8380Xeon Platinum 83807K14K21K28K35KMin: 42578.6 / Avg: 42770.83 / Max: 42890.8Min: 23393.5 / Avg: 23539.87 / Max: 23631.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Sharpen2 x Xeon Platinum 8380Xeon Platinum 8380150300450600750SE +/- 1.45, N = 36723701. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Sharpen2 x Xeon Platinum 8380Xeon Platinum 8380120240360480600Min: 670 / Avg: 672.33 / Max: 6751. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon Obj2 x Xeon Platinum 8380Xeon Platinum 83801632486480SE +/- 0.27, N = 3SE +/- 0.12, N = 372.4539.99MIN: 62.12 / MAX: 82.66MIN: 38.39 / MAX: 44.94
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon Obj2 x Xeon Platinum 8380Xeon Platinum 83801428425670Min: 72.13 / Avg: 72.45 / Max: 72.99Min: 39.8 / Avg: 39.99 / Max: 40.22

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1M2 x Xeon Platinum 8380Xeon Platinum 83806K12K18K24K30KSE +/- 67.30, N = 3SE +/- 6.99, N = 326504.214658.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1M2 x Xeon Platinum 8380Xeon Platinum 83805K10K15K20K25KMin: 26372 / Avg: 26504.2 / Max: 26592.2Min: 14644.3 / Avg: 14658.17 / Max: 14666.61. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83801224364860SE +/- 0.23, N = 3SE +/- 0.09, N = 328.2451.05
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83801020304050Min: 27.86 / Avg: 28.24 / Max: 28.65Min: 50.89 / Avg: 51.05 / Max: 51.21

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bare2 x Xeon Platinum 8380Xeon Platinum 83803691215SE +/- 0.005, N = 3SE +/- 0.010, N = 39.0635.0171. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bare2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 9.05 / Avg: 9.06 / Max: 9.07Min: 5 / Avg: 5.02 / Max: 5.041. (CXX) g++ options: -O3 -pthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Crown2 x Xeon Platinum 8380Xeon Platinum 83801428425670SE +/- 0.10, N = 5SE +/- 0.07, N = 364.7736.07MIN: 59.87 / MAX: 79.46MIN: 34.8 / MAX: 40.77
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Crown2 x Xeon Platinum 8380Xeon Platinum 83801326395265Min: 64.55 / Avg: 64.77 / Max: 65.05Min: 35.94 / Avg: 36.07 / Max: 36.16

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V22 x Xeon Platinum 8380Xeon Platinum 8380200K400K600K800K1000KSE +/- 1484.41, N = 3SE +/- 276.22, N = 35727501026060
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V22 x Xeon Platinum 8380Xeon Platinum 8380200K400K600K800K1000KMin: 571155 / Avg: 572750 / Max: 575716Min: 1025660 / Avg: 1026060 / Max: 1026590

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon Obj2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.40, N = 3SE +/- 0.05, N = 389.6250.10MIN: 70.4 / MAX: 98.44MIN: 46.69 / MAX: 54.05
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon Obj2 x Xeon Platinum 8380Xeon Platinum 838020406080100Min: 89.15 / Avg: 89.62 / Max: 90.41Min: 50 / Avg: 50.1 / Max: 50.16

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V42 x Xeon Platinum 8380Xeon Platinum 8380300K600K900K1200K1500KSE +/- 2539.56, N = 3SE +/- 1036.96, N = 36669671178463
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V42 x Xeon Platinum 8380Xeon Platinum 8380200K400K600K800K1000KMin: 662334 / Avg: 666967.33 / Max: 671086Min: 1176530 / Avg: 1178463.33 / Max: 1180080

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x Xeon Platinum 8380Xeon Platinum 838080K160K240K320K400KSE +/- 3489.62, N = 3SE +/- 596.42, N = 33551402015961. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x Xeon Platinum 8380Xeon Platinum 838060K120K180K240K300KMin: 348805 / Avg: 355139.67 / Max: 360844Min: 200567 / Avg: 201596 / Max: 2026331. (CXX) g++ options: -pipe -lpthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.C2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KSE +/- 106.40, N = 7SE +/- 41.49, N = 6100812.5457275.081. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.C2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KMin: 100490.94 / Avg: 100812.54 / Max: 101268.27Min: 57137.47 / Avg: 57275.08 / Max: 57377.231. (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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.C2 x Xeon Platinum 8380Xeon Platinum 83809K18K27K36K45KSE +/- 84.43, N = 8SE +/- 41.74, N = 640188.8422890.251. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.C2 x Xeon Platinum 8380Xeon Platinum 83807K14K21K28K35KMin: 39926.53 / Avg: 40188.84 / Max: 40553.93Min: 22770.31 / Avg: 22890.25 / Max: 23050.341. (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

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhanced2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 0.67, N = 3SE +/- 0.88, N = 311256411. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhanced2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000Min: 1124 / Avg: 1125.33 / Max: 1126Min: 640 / Avg: 641.33 / Max: 6431. (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

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasks2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KSE +/- 27.45, N = 6SE +/- 31.23, N = 47883137261. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasks2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KMin: 7813 / Avg: 7882.5 / Max: 8004Min: 13656 / Avg: 13726 / Max: 137941. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Degridding2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KSE +/- 404.92, N = 3SE +/- 5.70, N = 312928.807452.071. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Degridding2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KMin: 12493 / Avg: 12928.77 / Max: 13737.8Min: 7445.12 / Avg: 7452.07 / Max: 7463.381. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float2 x Xeon Platinum 8380Xeon Platinum 838012K24K36K48K60KSE +/- 83.39, N = 3SE +/- 122.59, N = 332738.956410.0
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float2 x Xeon Platinum 8380Xeon Platinum 838010K20K30K40K50KMin: 32632.1 / Avg: 32738.87 / Max: 32903.2Min: 56275.4 / Avg: 56410.03 / Max: 56654.8

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215SE +/- 0.08, N = 3SE +/- 0.00, N = 39.415.50MIN: 8.72 / MAX: 12.17MIN: 5.29 / MAX: 6.23
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 9.27 / Avg: 9.41 / Max: 9.56Min: 5.49 / Avg: 5.5 / Max: 5.5

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crown2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.26, N = 5SE +/- 0.09, N = 475.5044.17MIN: 65.3 / MAX: 94.46MIN: 42.27 / MAX: 48.76
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crown2 x Xeon Platinum 8380Xeon Platinum 83801530456075Min: 74.67 / Avg: 75.5 / Max: 76.03Min: 43.93 / Avg: 44.17 / Max: 44.34

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x40962 x Xeon Platinum 8380Xeon Platinum 83800.3240.6480.9721.2961.62SE +/- 0.00, N = 3SE +/- 0.00, N = 31.440.85
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x40962 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 1.43 / Avg: 1.44 / Max: 1.44Min: 0.85 / Avg: 0.85 / Max: 0.85

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C2 x Xeon Platinum 8380Xeon Platinum 838040K80K120K160K200KSE +/- 236.31, N = 4SE +/- 204.16, N = 3198052.38117333.471. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C2 x Xeon Platinum 8380Xeon Platinum 838030K60K90K120K150KMin: 197468.65 / Avg: 198052.38 / Max: 198558.7Min: 117004.88 / Avg: 117333.47 / Max: 117707.681. (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

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant2 x Xeon Platinum 8380Xeon Platinum 838012K24K36K48K60KSE +/- 253.99, N = 12SE +/- 71.21, N = 334155.057591.0
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant2 x Xeon Platinum 8380Xeon Platinum 838010K20K30K40K50KMin: 33526.1 / Avg: 34155.04 / Max: 36819.3Min: 57484.8 / Avg: 57591.03 / Max: 57726.3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KSE +/- 433.14, N = 7SE +/- 65.86, N = 347974.680455.7
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet2 x Xeon Platinum 8380Xeon Platinum 838014K28K42K56K70KMin: 47185.6 / Avg: 47974.57 / Max: 50234.5Min: 80352.2 / Avg: 80455.67 / Max: 80578

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 0.10, N = 3SE +/- 0.15, N = 344.4574.51
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Only2 x Xeon Platinum 8380Xeon Platinum 83801428425670Min: 44.25 / Avg: 44.45 / Max: 44.6Min: 74.24 / Avg: 74.51 / Max: 74.76

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.039, N = 5SE +/- 0.041, N = 39.25715.5151. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 9.13 / Avg: 9.26 / Max: 9.38Min: 15.46 / Avg: 15.52 / Max: 15.591. (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

This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.32 x Xeon Platinum 8380Xeon Platinum 8380400K800K1200K1600K2000KSE +/- 19700.68, N = 15SE +/- 17257.96, N = 15203598612155871. (CC) gcc options: -pthread -lpthread -O3 -march=native
OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.32 x Xeon Platinum 8380Xeon Platinum 8380400K800K1200K1600K2000KMin: 1901668 / Avg: 2035985.93 / Max: 2171685Min: 1095677 / Avg: 1215587.4 / Max: 13215571. (CC) gcc options: -pthread -lpthread -O3 -march=native

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material Tester2 x Xeon Platinum 8380Xeon Platinum 83804080120160200177.78106.17

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x21602 x Xeon Platinum 8380Xeon Platinum 83800.67051.3412.01152.6823.3525SE +/- 0.00, N = 5SE +/- 0.00, N = 32.981.78
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x21602 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.98 / Avg: 2.98 / Max: 2.99Min: 1.77 / Avg: 1.78 / Max: 1.78

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 Buckyball2 x Xeon Platinum 8380Xeon Platinum 838070014002100280035001846.83085.11. (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

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x21602 x Xeon Platinum 8380Xeon Platinum 83800.67281.34562.01842.69123.364SE +/- 0.00, N = 5SE +/- 0.00, N = 32.991.79
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x21602 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.97 / Avg: 2.99 / Max: 3Min: 1.79 / Avg: 1.79 / Max: 1.79

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbig2 x Xeon Platinum 8380Xeon Platinum 8380612182430SE +/- 0.01, N = 4SE +/- 0.02, N = 314.4123.841. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbig2 x Xeon Platinum 8380Xeon Platinum 8380612182430Min: 14.4 / Avg: 14.41 / Max: 14.44Min: 23.82 / Avg: 23.84 / Max: 23.871. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83801.20972.41943.62914.83886.0485SE +/- 0.00173, N = 3SE +/- 0.01029, N = 33.259125.37652MIN: 3.09MIN: 5.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 3.26 / Avg: 3.26 / Max: 3.26Min: 5.36 / Avg: 5.38 / Max: 5.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83801.32172.64343.96515.28686.6085SE +/- 0.00332, N = 9SE +/- 0.00133, N = 93.563965.87433MIN: 3.49MIN: 5.711. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 3.55 / Avg: 3.56 / Max: 3.58Min: 5.87 / Avg: 5.87 / Max: 5.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30M2 x Xeon Platinum 8380Xeon Platinum 8380612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 314.3023.491. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30M2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 14.27 / Avg: 14.3 / Max: 14.36Min: 23.46 / Avg: 23.49 / Max: 23.531. (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

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.30860.61720.92581.23441.543SE +/- 0.000669, N = 9SE +/- 0.000612, N = 90.8395561.371550MIN: 0.8MIN: 1.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 0.84 / Avg: 0.84 / Max: 0.84Min: 1.37 / Avg: 1.37 / Max: 1.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Ninja2 x Xeon Platinum 8380Xeon Platinum 838050100150200250SE +/- 0.54, N = 3SE +/- 0.93, N = 3127.99208.65
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Ninja2 x Xeon Platinum 8380Xeon Platinum 83804080120160200Min: 127.2 / Avg: 127.99 / Max: 129.04Min: 207.08 / Avg: 208.65 / Max: 210.3

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.06980.13960.20940.27920.349SE +/- 0.000612, N = 9SE +/- 0.002283, N = 150.1906280.310362MIN: 0.18MIN: 0.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838012345Min: 0.19 / Avg: 0.19 / Max: 0.19Min: 0.3 / Avg: 0.31 / Max: 0.341. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.33360.66721.00081.33441.668SE +/- 0.002416, N = 7SE +/- 0.000981, N = 70.9150861.482560MIN: 0.85MIN: 1.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 0.91 / Avg: 0.92 / Max: 0.92Min: 1.48 / Avg: 1.48 / Max: 1.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.14, N = 3SE +/- 0.04, N = 314.338.95MIN: 11.53 / MAX: 18.29MIN: 7.51 / MAX: 10.05
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 14.07 / Avg: 14.33 / Max: 14.53Min: 8.88 / Avg: 8.95 / Max: 9.02

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Hair2 x Xeon Platinum 8380Xeon Platinum 83803691215SE +/- 0.05061, N = 8SE +/- 0.04039, N = 55.733319.154461. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Hair2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 5.58 / Avg: 5.73 / Max: 6Min: 9 / Avg: 9.15 / Max: 9.231. (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

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.2160.4320.6480.8641.08SE +/- 0.001365, N = 4SE +/- 0.001560, N = 40.6043780.960174MIN: 0.56MIN: 0.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 0.6 / Avg: 0.6 / Max: 0.61Min: 0.96 / Avg: 0.96 / Max: 0.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k Atoms2 x Xeon Platinum 8380Xeon Platinum 8380816243240SE +/- 0.03, N = 3SE +/- 0.09, N = 335.9922.681. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k Atoms2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 35.95 / Avg: 35.99 / Max: 36.04Min: 22.52 / Avg: 22.68 / Max: 22.831. (CXX) g++ options: -O3 -pthread -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380918273645SE +/- 0.32, N = 3SE +/- 0.06, N = 337.4923.701. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 37.07 / Avg: 37.49 / Max: 38.12Min: 23.63 / Avg: 23.7 / Max: 23.821. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian Hydrodynamics2 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.04, N = 5SE +/- 0.01, N = 410.0815.921. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian Hydrodynamics2 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 9.96 / Avg: 10.08 / Max: 10.15Min: 15.89 / Avg: 15.92 / Max: 15.941. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.07, N = 3SE +/- 0.02, N = 36.974.42MIN: 3.13 / MAX: 8.11MIN: 1.74 / MAX: 5.11
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 6.84 / Avg: 6.97 / Max: 7.07Min: 4.39 / Avg: 4.42 / Max: 4.44

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380306090120150SE +/- 0.22, N = 3SE +/- 0.25, N = 390.57142.51
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380306090120150Min: 90.13 / Avg: 90.57 / Max: 90.81Min: 142.13 / Avg: 142.51 / Max: 142.97

Quantum ESPRESSO

Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.7Input: AUSURF1122 x Xeon Platinum 8380Xeon Platinum 8380400800120016002000SE +/- 12.08, N = 9SE +/- 29.35, N = 91169.151783.191. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.7Input: AUSURF1122 x Xeon Platinum 8380Xeon Platinum 838030060090012001500Min: 1075.49 / Avg: 1169.15 / Max: 1193.99Min: 1615.19 / Avg: 1783.19 / Max: 1883.11. (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

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein2 x Xeon Platinum 8380Xeon Platinum 8380714212835SE +/- 0.33, N = 15SE +/- 0.23, N = 1531.5620.841. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 29.36 / Avg: 31.56 / Max: 33.91Min: 19.02 / Avg: 20.84 / Max: 22.161. (CXX) g++ options: -O3 -pthread -lm

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirl2 x Xeon Platinum 8380Xeon Platinum 83805001000150020002500SE +/- 4.10, N = 3SE +/- 0.67, N = 3219114521. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirl2 x Xeon Platinum 8380Xeon Platinum 8380400800120016002000Min: 2185 / Avg: 2191.33 / Max: 2199Min: 1451 / Avg: 1451.67 / Max: 14531. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Degridding2 x Xeon Platinum 8380Xeon Platinum 83805K10K15K20K25KSE +/- 396.15, N = 8SE +/- 195.78, N = 524810.216445.21. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Degridding2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KMin: 24205.1 / Avg: 24810.23 / Max: 26625.6Min: 15662.1 / Avg: 16445.22 / Max: 166411. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380714212835SE +/- 0.24, N = 5SE +/- 0.41, N = 321.6332.01
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 21.36 / Avg: 21.63 / Max: 22.58Min: 31.57 / Avg: 32.01 / Max: 32.84

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 32 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.04, N = 4SE +/- 0.01, N = 315.5122.871. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 32 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 15.45 / Avg: 15.51 / Max: 15.61Min: 22.85 / Avg: 22.87 / Max: 22.881. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.28510.57020.85531.14041.4255SE +/- 0.010254, N = 9SE +/- 0.006531, N = 151.2670000.872017MIN: 0.86MIN: 0.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 1.21 / Avg: 1.27 / Max: 1.31Min: 0.84 / Avg: 0.87 / Max: 0.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

KeyDB

A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.162 x Xeon Platinum 8380Xeon Platinum 8380170K340K510K680K850KSE +/- 5876.97, N = 15SE +/- 10511.44, N = 3541996.24771533.421. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.162 x Xeon Platinum 8380Xeon Platinum 8380130K260K390K520K650KMin: 505353.63 / Avg: 541996.24 / Max: 586269.7Min: 750542.18 / Avg: 771533.42 / Max: 783027.681. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fast2 x Xeon Platinum 8380Xeon Platinum 8380918273645SE +/- 0.19, N = 4SE +/- 0.02, N = 338.7127.571. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fast2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 38.36 / Avg: 38.71 / Max: 39.06Min: 27.53 / Avg: 27.57 / Max: 27.61. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While Writing2 x Xeon Platinum 8380Xeon Platinum 83802M4M6M8M10MSE +/- 103809.83, N = 15SE +/- 63537.44, N = 3917026066765561. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While Writing2 x Xeon Platinum 8380Xeon Platinum 83801.6M3.2M4.8M6.4M8MMin: 8582562 / Avg: 9170259.73 / Max: 9988533Min: 6612056 / Avg: 6676556 / Max: 68036261. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 8380140280420560700SE +/- 5.49, N = 3SE +/- 2.17, N = 34826591. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 8380120240360480600Min: 473 / Avg: 482.33 / Max: 492Min: 655.5 / Avg: 659.17 / Max: 6631. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.10, N = 3SE +/- 0.05, N = 316.4322.32
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 16.33 / Avg: 16.43 / Max: 16.62Min: 22.24 / Avg: 22.32 / Max: 22.42

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney Material2 x Xeon Platinum 8380Xeon Platinum 83802040608010057.4077.52

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.90711.81422.72133.62844.5355SE +/- 0.00418, N = 4SE +/- 0.02087, N = 42.994854.03139MIN: 2.85MIN: 3.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.98 / Avg: 2.99 / Max: 3Min: 3.98 / Avg: 4.03 / Max: 4.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix Makefiles2 x Xeon Platinum 8380Xeon Platinum 838060120180240300SE +/- 0.65, N = 3SE +/- 0.72, N = 3190.68256.63
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix Makefiles2 x Xeon Platinum 8380Xeon Platinum 838050100150200250Min: 189.87 / Avg: 190.68 / Max: 191.98Min: 255.33 / Avg: 256.63 / Max: 257.83

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Gridding2 x Xeon Platinum 8380Xeon Platinum 83804K8K12K16K20KSE +/- 158.49, N = 8SE +/- 155.70, N = 518859.814169.21. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - Gridding2 x Xeon Platinum 8380Xeon Platinum 83803K6K9K12K15KMin: 17750.4 / Avg: 18859.81 / Max: 19018.3Min: 14013.5 / Avg: 14169.2 / Max: 147921. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.27270.54540.81811.09081.3635SE +/- 0.003790, N = 4SE +/- 0.000855, N = 40.9148651.212030MIN: 0.85MIN: 1.161. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 0.91 / Avg: 0.91 / Max: 0.93Min: 1.21 / Avg: 1.21 / Max: 1.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.D2 x Xeon Platinum 8380Xeon Platinum 83807001400210028003500SE +/- 20.88, N = 4SE +/- 6.51, N = 33086.242333.561. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.D2 x Xeon Platinum 8380Xeon Platinum 83805001000150020002500Min: 3048.86 / Avg: 3086.24 / Max: 3140.91Min: 2321.6 / Avg: 2333.56 / Max: 2343.981. (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

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.07420.14840.22260.29680.371SE +/- 0.000574, N = 4SE +/- 0.000427, N = 40.2496110.329636MIN: 0.23MIN: 0.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838012345Min: 0.25 / Avg: 0.25 / Max: 0.25Min: 0.33 / Avg: 0.33 / Max: 0.331. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.024, N = 8SE +/- 0.007, N = 74.7096.2111. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 4.62 / Avg: 4.71 / Max: 4.86Min: 6.19 / Avg: 6.21 / Max: 6.251. (CXX) g++ options: -O2 -lOpenCL

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Summer Nature 4K2 x Xeon Platinum 8380Xeon Platinum 8380120240360480600SE +/- 0.65, N = 3SE +/- 0.60, N = 3532.57404.27MIN: 189.3 / MAX: 586.86MIN: 275.43 / MAX: 456.481. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Summer Nature 4K2 x Xeon Platinum 8380Xeon Platinum 838090180270360450Min: 531.27 / Avg: 532.57 / Max: 533.36Min: 403.07 / Avg: 404.27 / Max: 404.951. (CC) gcc options: -pthread -lm

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 2562 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 1.84, N = 3SE +/- 1.12, N = 36979181. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 2562 x Xeon Platinum 8380Xeon Platinum 8380160320480640800Min: 694.44 / Avg: 697.36 / Max: 700.77Min: 916.59 / Avg: 917.71 / Max: 919.961. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 5122 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 2.75, N = 3SE +/- 0.76, N = 36648701. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 5122 x Xeon Platinum 8380Xeon Platinum 8380150300450600750Min: 659.2 / Avg: 664.47 / Max: 668.45Min: 868.81 / Avg: 869.57 / Max: 871.081. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -ldl -lz -lrt

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 22 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.02, N = 4SE +/- 0.02, N = 411.4214.931. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 22 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 11.38 / Avg: 11.41 / Max: 11.46Min: 14.9 / Avg: 14.93 / Max: 151. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 32 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.005, N = 8SE +/- 0.006, N = 74.6586.013
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 32 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 4.65 / Avg: 4.66 / Max: 4.69Min: 6 / Avg: 6.01 / Max: 6.05

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmark2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 3.53, N = 3820641MIN: 1 / MAX: 3230MIN: 1 / MAX: 2858
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmark2 x Xeon Platinum 8380Xeon Platinum 8380140280420560700Min: 813 / Avg: 819.67 / Max: 825

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussian2 x Xeon Platinum 8380Xeon Platinum 8380160320480640800SE +/- 2.03, N = 3SE +/- 2.33, N = 37325861. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussian2 x Xeon Platinum 8380Xeon Platinum 8380130260390520650Min: 728 / Avg: 731.67 / Max: 735Min: 581 / Avg: 585.67 / Max: 5881. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: Small2 x Xeon Platinum 8380Xeon Platinum 83806K12K18K24K30KSE +/- 90.91, N = 4SE +/- 13.81, N = 428391.423125.01. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: Small2 x Xeon Platinum 8380Xeon Platinum 83805K10K15K20K25KMin: 28190.3 / Avg: 28391.38 / Max: 28610.6Min: 23098.7 / Avg: 23124.98 / Max: 23162.21. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 2.14, N = 3SE +/- 4.02, N = 3675.16812.26MIN: 645.81MIN: 778.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380140280420560700Min: 671.14 / Avg: 675.16 / Max: 678.47Min: 807.86 / Avg: 812.26 / Max: 820.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed ImageMagick Compilation

This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile2 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.14, N = 4SE +/- 0.06, N = 411.9614.37
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile2 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 11.56 / Avg: 11.96 / Max: 12.2Min: 14.23 / Avg: 14.37 / Max: 14.5

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 0.92, N = 3SE +/- 2.62, N = 3675.12810.36MIN: 649.43MIN: 779.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380140280420560700Min: 673.3 / Avg: 675.12 / Max: 676.23Min: 806.68 / Avg: 810.36 / Max: 815.421. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compile2 x Xeon Platinum 8380Xeon Platinum 83801326395265SE +/- 0.08, N = 3SE +/- 0.18, N = 348.0756.58
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compile2 x Xeon Platinum 8380Xeon Platinum 83801122334455Min: 47.95 / Avg: 48.07 / Max: 48.23Min: 56.27 / Avg: 56.58 / Max: 56.9

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.03, N = 3SE +/- 0.05, N = 36.217.30
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 6.17 / Avg: 6.21 / Max: 6.28Min: 7.21 / Avg: 7.3 / Max: 7.39

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile2 x Xeon Platinum 8380Xeon Platinum 83801530456075SE +/- 0.32, N = 3SE +/- 0.25, N = 357.6467.16
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile2 x Xeon Platinum 8380Xeon Platinum 83801326395265Min: 57.01 / Avg: 57.64 / Max: 58.08Min: 66.69 / Avg: 67.16 / Max: 67.54

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.12, N = 3SE +/- 0.01, N = 318.7121.79
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 18.56 / Avg: 18.71 / Max: 18.94Min: 21.79 / Avg: 21.79 / Max: 21.81

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 5.94, N = 10SE +/- 11.50, N = 37538671. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate2 x Xeon Platinum 8380Xeon Platinum 8380150300450600750Min: 721 / Avg: 753 / Max: 770Min: 844 / Avg: 867 / Max: 8791. (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

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 192 x Xeon Platinum 8380Xeon Platinum 83803691215SE +/- 0.024, N = 5SE +/- 0.026, N = 59.11110.387
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 192 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 9.03 / Avg: 9.11 / Max: 9.16Min: 10.32 / Avg: 10.39 / Max: 10.47

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Emily2 x Xeon Platinum 8380Xeon Platinum 8380306090120150123.70140.51

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 8380130260390520650SE +/- 8.14, N = 12SE +/- 6.23, N = 55165861. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500Min: 471 / Avg: 516.13 / Max: 556Min: 571 / Avg: 585.6 / Max: 608.51. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.063, N = 15SE +/- 0.063, N = 157.6526.7621. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 7.04 / Avg: 7.65 / Max: 7.99Min: 6.64 / Avg: 6.76 / Max: 7.641. (CXX) g++ options: -O2 -lOpenCL

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fast2 x Xeon Platinum 8380Xeon Platinum 83801122334455SE +/- 0.33, N = 4SE +/- 0.08, N = 447.8442.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fast2 x Xeon Platinum 8380Xeon Platinum 83801020304050Min: 47.1 / Avg: 47.84 / Max: 48.52Min: 42.52 / Avg: 42.65 / Max: 42.831. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.45470.90941.36411.81882.2735SE +/- 0.00217, N = 5SE +/- 0.00210, N = 51.812712.02106MIN: 1.67MIN: 1.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 1.81 / Avg: 1.81 / Max: 1.82Min: 2.01 / Avg: 2.02 / Max: 2.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 2.33, N = 3104211591. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000Min: 1038 / Avg: 1042.33 / Max: 10461. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Chimera 1080p 10-bit2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 1.95, N = 3SE +/- 0.41, N = 3861.39775.38MIN: 524.86 / MAX: 1144.29MIN: 588.21 / MAX: 1071.61. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Chimera 1080p 10-bit2 x Xeon Platinum 8380Xeon Platinum 8380150300450600750Min: 857.51 / Avg: 861.39 / Max: 863.72Min: 774.63 / Avg: 775.38 / Max: 776.041. (CC) gcc options: -pthread -lm

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-Exponential2 x Xeon Platinum 8380Xeon Platinum 83800.63281.26561.89842.53123.164SE +/- 0.01197, N = 10SE +/- 0.00595, N = 102.565962.812481. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-Exponential2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 2.52 / Avg: 2.57 / Max: 2.65Min: 2.78 / Avg: 2.81 / Max: 2.841. (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

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KSE +/- 439.19, N = 3SE +/- 82.87, N = 374702.481669.1
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile2 x Xeon Platinum 8380Xeon Platinum 838014K28K42K56K70KMin: 74113.6 / Avg: 74702.4 / Max: 75561.3Min: 81553.4 / Avg: 81669.07 / Max: 81829.7

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 8380714212835SE +/- 0.08, N = 3SE +/- 0.06, N = 328.6531.231. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 28.52 / Avg: 28.65 / Max: 28.8Min: 31.11 / Avg: 31.23 / Max: 31.311. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500SE +/- 1.03, N = 3SE +/- 1.28, N = 3439.37476.02MIN: 423.06MIN: 462.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838080160240320400Min: 437.6 / Avg: 439.37 / Max: 441.16Min: 473.48 / Avg: 476.02 / Max: 477.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500SE +/- 2.02, N = 3SE +/- 0.97, N = 3439.64476.21MIN: 422.12MIN: 462.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838080160240320400Min: 436.81 / Avg: 439.64 / Max: 443.56Min: 474.28 / Avg: 476.21 / Max: 477.281. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed PHP Compilation

This test times how long it takes to build PHP 7. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380918273645SE +/- 0.05, N = 3SE +/- 0.13, N = 335.3438.27
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 35.27 / Avg: 35.34 / Max: 35.44Min: 38.01 / Avg: 38.27 / Max: 38.45

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838070140210280350SE +/- 2.91, N = 15SE +/- 0.54, N = 10313.93290.361. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838060120180240300Min: 301.51 / Avg: 313.93 / Max: 340.33Min: 288.18 / Avg: 290.36 / Max: 292.831. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500SE +/- 2.16, N = 3SE +/- 1.74, N = 3441.26475.86MIN: 423.47MIN: 461.871. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838080160240320400Min: 437.36 / Avg: 441.26 / Max: 444.81Min: 473.21 / Avg: 475.86 / Max: 479.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 83802K4K6K8K10KSE +/- 2.92, N = 3SE +/- 18.20, N = 3840290561. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 838016003200480064008000Min: 8396.5 / Avg: 8402.33 / Max: 8405.5Min: 9022.5 / Avg: 9056.17 / Max: 90851. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380816243240SE +/- 0.33, N = 3SE +/- 0.21, N = 333.4331.06
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 32.76 / Avg: 33.43 / Max: 33.8Min: 30.8 / Avg: 31.06 / Max: 31.48

Timed GDB GNU Debugger Compilation

This test times how long it takes to build the GNU Debugger (GDB) in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 10.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 83801020304050SE +/- 0.06, N = 3SE +/- 0.06, N = 339.8442.71
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 10.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380918273645Min: 39.77 / Avg: 39.84 / Max: 39.95Min: 42.64 / Avg: 42.71 / Max: 42.82

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Gridding2 x Xeon Platinum 8380Xeon Platinum 838011002200330044005500SE +/- 46.19, N = 3SE +/- 4.90, N = 34997.055305.671. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - Gridding2 x Xeon Platinum 8380Xeon Platinum 83809001800270036004500Min: 4923.83 / Avg: 4997.05 / Max: 5082.43Min: 5295.99 / Avg: 5305.67 / Max: 5311.841. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.08190.16380.24570.32760.4095SE +/- 0.001200, N = 3SE +/- 0.000930, N = 30.3639770.343258MIN: 0.32MIN: 0.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838012345Min: 0.36 / Avg: 0.36 / Max: 0.37Min: 0.34 / Avg: 0.34 / Max: 0.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.32840.65680.98521.31361.642SE +/- 0.00305, N = 7SE +/- 0.00041, N = 71.397171.45952MIN: 1.24MIN: 1.431. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 1.39 / Avg: 1.4 / Max: 1.41Min: 1.46 / Avg: 1.46 / Max: 1.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.32110.64220.96331.28441.6055SE +/- 0.00190, N = 5SE +/- 0.00142, N = 51.367681.42703MIN: 1.33MIN: 1.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810Min: 1.36 / Avg: 1.37 / Max: 1.37Min: 1.42 / Avg: 1.43 / Max: 1.431. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380918273645SE +/- 0.31, N = 3SE +/- 0.12, N = 338.5136.97
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPU2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 38.2 / Avg: 38.51 / Max: 39.12Min: 36.81 / Avg: 36.97 / Max: 37.2

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 83804080120160200SE +/- 1.69, N = 3SE +/- 1.48, N = 31972041. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 83804080120160200Min: 194.5 / Avg: 196.67 / Max: 200Min: 201.5 / Avg: 204.33 / Max: 206.51. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380110220330440550SE +/- 1.83, N = 10SE +/- 0.89, N = 11469.70485.541. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838090180270360450Min: 460.63 / Avg: 469.7 / Max: 478Min: 477.7 / Avg: 485.54 / Max: 489.831. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water Caustic2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 320.3020.911. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water Caustic2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 20.27 / Avg: 20.3 / Max: 20.33Min: 20.86 / Avg: 20.91 / Max: 20.961. (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

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 100, Lossless Compression2 x Xeon Platinum 8380Xeon Platinum 838090180270360450SE +/- 0.04, N = 3SE +/- 0.09, N = 3413.22425.321. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 100, Lossless Compression2 x Xeon Platinum 8380Xeon Platinum 838080160240320400Min: 413.17 / Avg: 413.22 / Max: 413.31Min: 425.22 / Avg: 425.32 / Max: 425.491. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless2 x Xeon Platinum 8380Xeon Platinum 8380714212835SE +/- 0.31, N = 3SE +/- 0.18, N = 329.6930.531. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless2 x Xeon Platinum 8380Xeon Platinum 8380714212835Min: 29.36 / Avg: 29.69 / Max: 30.31Min: 30.17 / Avg: 30.53 / Max: 30.741. (CXX) g++ options: -O3 -fPIC -lm

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 95, Compression Effort 72 x Xeon Platinum 8380Xeon Platinum 838050100150200250SE +/- 0.08, N = 3SE +/- 0.08, N = 3218.16223.971. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 95, Compression Effort 72 x Xeon Platinum 8380Xeon Platinum 83804080120160200Min: 218.02 / Avg: 218.16 / Max: 218.29Min: 223.81 / Avg: 223.97 / Max: 224.091. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 75, Compression Effort 72 x Xeon Platinum 8380Xeon Platinum 8380306090120150SE +/- 0.06, N = 3SE +/- 0.05, N = 3117.57120.691. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 75, Compression Effort 72 x Xeon Platinum 8380Xeon Platinum 838020406080100Min: 117.46 / Avg: 117.57 / Max: 117.66Min: 120.59 / Avg: 120.69 / Max: 120.751. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.05270.10540.15810.21080.2635SE +/- 0.001610, N = 4SE +/- 0.000310, N = 40.2286320.234327MIN: 0.2MIN: 0.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838012345Min: 0.22 / Avg: 0.23 / Max: 0.23Min: 0.23 / Avg: 0.23 / Max: 0.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83800.09870.19740.29610.39480.4935SE +/- 0.001219, N = 5SE +/- 0.000558, N = 50.4385110.427987MIN: 0.4MIN: 0.411. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 838012345Min: 0.44 / Avg: 0.44 / Max: 0.44Min: 0.43 / Avg: 0.43 / Max: 0.431. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMP2 x Xeon Platinum 8380Xeon Platinum 838030060090012001500SE +/- 11.55, N = 4SE +/- 14.64, N = 41238.711266.331. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMP2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000Min: 1219.51 / Avg: 1238.71 / Max: 1265.82Min: 1234.57 / Avg: 1266.33 / Max: 1298.71. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500SE +/- 5.22, N = 15SE +/- 4.09, N = 15475.45485.121. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838090180270360450Min: 405.19 / Avg: 475.45 / Max: 488.54Min: 428.98 / Avg: 485.12 / Max: 494.481. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Kripke

Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.42 x Xeon Platinum 8380Xeon Platinum 838040M80M120M160M200MSE +/- 1334158.46, N = 15SE +/- 953041.14, N = 31789652331758903001. (CXX) g++ options: -O3 -fopenmp
OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.42 x Xeon Platinum 8380Xeon Platinum 838030M60M90M120M150MMin: 173860400 / Avg: 178965233.33 / Max: 189478000Min: 174362300 / Avg: 175890300 / Max: 1776411001. (CXX) g++ options: -O3 -fopenmp

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 100, Compression Effort 52 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.007, N = 6SE +/- 0.002, N = 66.2516.3031. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20210126Encode Settings: Quality 100, Compression Effort 52 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 6.23 / Avg: 6.25 / Max: 6.28Min: 6.3 / Avg: 6.3 / Max: 6.311. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838080160240320400SE +/- 2.30, N = 9SE +/- 2.16, N = 10371.88370.641. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 838070140210280350Min: 363.51 / Avg: 371.88 / Max: 382.09Min: 358.83 / Avg: 370.64 / Max: 380.781. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380130260390520650SE +/- 3.29, N = 11SE +/- 1.28, N = 12584.72583.641. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p2 x Xeon Platinum 8380Xeon Platinum 8380100200300400500Min: 570.34 / Avg: 584.72 / Max: 601.81Min: 579.15 / Avg: 583.64 / Max: 595.241. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolume2 x Xeon Platinum 8380Xeon Platinum 83806M12M18M24M30MSE +/- 89609.36, N = 3SE +/- 65507.38, N = 32914304429092155MIN: 1069452 / MAX: 176387184MIN: 1047483 / MAX: 175929480
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolume2 x Xeon Platinum 8380Xeon Platinum 83805M10M15M20M25MMin: 28965041 / Avg: 29143044 / Max: 29250093Min: 28968038 / Avg: 29092154.67 / Max: 29190544

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill Sync2 x Xeon Platinum 8380Xeon Platinum 8380100K200K300K400K500KSE +/- 556.11, N = 3SE +/- 985.63, N = 34821914815041. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill Sync2 x Xeon Platinum 8380Xeon Platinum 838080K160K240K320K400KMin: 481401 / Avg: 482191 / Max: 483264Min: 479762 / Avg: 481504.33 / Max: 4831741. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping2 x Xeon Platinum 8380Xeon Platinum 838030060090012001500SE +/- 13.05, N = 3SE +/- 3.16, N = 31354.591356.011. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000Min: 1329.08 / Avg: 1354.59 / Max: 1372.12Min: 1351.9 / Avg: 1356.01 / Max: 1362.211. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolume2 x Xeon Platinum 8380Xeon Platinum 838020M40M60M80M100MSE +/- 177762.64, N = 3SE +/- 47834.23, N = 3104922070105023963MIN: 1391949 / MAX: 891929412MIN: 1379843 / MAX: 899785764
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolume2 x Xeon Platinum 8380Xeon Platinum 838020M40M60M80M100MMin: 104568472 / Avg: 104922069.67 / Max: 105130887Min: 104937888 / Avg: 105023963.33 / Max: 105103162

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380918273645SE +/- 0.14, N = 3SE +/- 0.18, N = 337.6937.681. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380816243240Min: 37.43 / Avg: 37.69 / Max: 37.91Min: 37.35 / Avg: 37.68 / Max: 37.981. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 319.7919.79
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile2 x Xeon Platinum 8380Xeon Platinum 8380510152025Min: 19.77 / Avg: 19.79 / Max: 19.81Min: 19.78 / Avg: 19.79 / Max: 19.8

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ExhaustiveXeon Platinum 8380 rest510152025SE +/- 0.02, N = 319.601. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ThoroughXeon Platinum 8380 rest246810SE +/- 0.0247, N = 37.41071. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: MediumXeon Platinum 8380 rest1.09152.1833.27454.3665.4575SE +/- 0.0185, N = 34.85121. (CXX) g++ options: -O3 -flto -pthread

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pXeon Platinum 8380 rest612182430SE +/- 0.02, N = 325.461. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 1080pXeon Platinum 8380 rest3691215SE +/- 0.01, N = 311.801. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KXeon Platinum 8380 rest48121620SE +/- 0.07, N = 313.971. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KXeon Platinum 8380 rest1.27582.55163.82745.10326.379SE +/- 0.00, N = 35.671. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAMXeon Platinum 8380 rest20406080100SE +/- 0.06, N = 395.91. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAMXeon Platinum 8380 rest306090120150SE +/- 0.12, N = 3132.21. (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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMXeon Platinum 8380 rest1632486480SE +/- 0.21, N = 371.41. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMXeon Platinum 8380 rest20406080100SE +/- 0.52, N = 398.31. (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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMXeon Platinum 8380 rest50100150200250SE +/- 0.49, N = 3207.51. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMXeon Platinum 8380 rest70140210280350SE +/- 1.16, N = 3306.81. (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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMXeon Platinum 8380 rest306090120150SE +/- 0.60, N = 3129.61. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMXeon Platinum 8380 rest70140210280350SE +/- 0.12, N = 3305.61. (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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMXeon Platinum 8380 rest4080120160200SE +/- 0.03, N = 3174.31. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMXeon Platinum 8380 rest60120180240300SE +/- 0.45, N = 3273.21. (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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMXeon Platinum 8380 rest20406080100SE +/- 2.67, N = 3110.11. (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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.04Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMXeon Platinum 8380 rest60120180240300SE +/- 0.25, N = 3279.91. (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

OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 21.04Test: OFDM_TestXeon Platinum 8380 rest30M60M90M120M150MSE +/- 305505.05, N = 31204000001. (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

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 838016003200480064008000SE +/- 15.90, N = 3SE +/- 184.76, N = 12760963811. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPU2 x Xeon Platinum 8380Xeon Platinum 838013002600390052006500Min: 7590.5 / Avg: 7608.83 / Max: 7640.5Min: 5236.5 / Avg: 6380.71 / Max: 74221. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: LBC, LBRY Credits2 x Xeon Platinum 8380Xeon Platinum 838090K180K270K360K450KSE +/- 30611.01, N = 12SE +/- 7613.62, N = 124027262737801. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: LBC, LBRY Credits2 x Xeon Platinum 8380Xeon Platinum 838070K140K210K280K350KMin: 223880 / Avg: 402725.83 / Max: 532950Min: 197030 / Avg: 273780 / Max: 2915501. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Myriad-Groestl2 x Xeon Platinum 8380Xeon Platinum 838020K40K60K80K100KSE +/- 1515.66, N = 15SE +/- 5943.89, N = 1584872757071. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Myriad-Groestl2 x Xeon Platinum 8380Xeon Platinum 838015K30K45K60K75KMin: 77250 / Avg: 84872 / Max: 99860Min: 58020 / Avg: 75706.67 / Max: 1220101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Skeincoin2 x Xeon Platinum 8380Xeon Platinum 8380170K340K510K680K850KSE +/- 19372.86, N = 12SE +/- 23435.25, N = 127741634075021. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Skeincoin2 x Xeon Platinum 8380Xeon Platinum 8380130K260K390K520K650KMin: 611710 / Avg: 774163.33 / Max: 862880Min: 246090 / Avg: 407501.67 / Max: 5067001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Blake-2 S2 x Xeon Platinum 8380Xeon Platinum 8380800K1600K2400K3200K4000KSE +/- 58124.19, N = 12SE +/- 117578.84, N = 12366234824763031. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Blake-2 S2 x Xeon Platinum 8380Xeon Platinum 8380600K1200K1800K2400K3000KMin: 3427360 / Avg: 3662347.5 / Max: 4082120Min: 1318010 / Avg: 2476302.5 / Max: 28648901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Deepcoin2 x Xeon Platinum 8380Xeon Platinum 838016K32K48K64K80KSE +/- 2190.61, N = 15SE +/- 1301.01, N = 1575061335831. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: Deepcoin2 x Xeon Platinum 8380Xeon Platinum 838013K26K39K52K65KMin: 54420 / Avg: 75061.33 / Max: 86660Min: 28420 / Avg: 33583.33 / Max: 440001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: x25x2 x Xeon Platinum 8380Xeon Platinum 83806001200180024003000SE +/- 50.45, N = 15SE +/- 14.01, N = 32725.031022.321. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: x25x2 x Xeon Platinum 8380Xeon Platinum 83805001000150020002500Min: 2151.25 / Avg: 2725.03 / Max: 2933.54Min: 994.34 / Avg: 1022.32 / Max: 1037.571. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83802004006008001000SE +/- 68.99, N = 15SE +/- 2.97, N = 3757.06813.03MIN: 648.2MIN: 779.611. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380140280420560700Min: 673.21 / Avg: 757.06 / Max: 1716.52Min: 807.31 / Avg: 813.02 / Max: 817.261. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.01372, N = 3SE +/- 0.21071, N = 126.969104.51612MIN: 6.54MIN: 3.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 6.94 / Avg: 6.97 / Max: 6.99Min: 3.49 / Avg: 4.52 / Max: 5.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

YafaRay

YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scene2 x Xeon Platinum 8380Xeon Platinum 838020406080100SE +/- 2.28, N = 15SE +/- 1.05, N = 381.5174.901. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scene2 x Xeon Platinum 8380Xeon Platinum 83801632486480Min: 70.66 / Avg: 81.51 / Max: 94.8Min: 72.97 / Avg: 74.9 / Max: 76.561. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 838048121620SE +/- 0.63, N = 15SE +/- 0.27, N = 1514.1114.39MIN: 10.63 / MAX: 19.45MIN: 12.31 / MAX: 19.48
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 838048121620Min: 11.34 / Avg: 14.11 / Max: 19.39Min: 13.42 / Avg: 14.39 / Max: 17.93

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 8380246810SE +/- 0.14, N = 15SE +/- 0.06, N = 156.894.50MIN: 2.38 / MAX: 8.45MIN: 1.72 / MAX: 5.53
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPU2 x Xeon Platinum 8380Xeon Platinum 83803691215Min: 5.7 / Avg: 6.89 / Max: 7.37Min: 4.16 / Avg: 4.5 / Max: 4.8

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocyte2 x Xeon Platinum 8380Xeon Platinum 83801122334455SE +/- 0.66, N = 3SE +/- 0.81, N = 1547.4444.021. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocyte2 x Xeon Platinum 8380Xeon Platinum 83801020304050Min: 46.54 / Avg: 47.44 / Max: 48.74Min: 39.8 / Avg: 44.02 / Max: 49.81. (CXX) g++ options: -O2 -lOpenCL

214 Results Shown

BRL-CAD
Cpuminer-Opt:
  Magi
  Garlicoin
SVT-AV1:
  Preset 8 - Bosphorus 4K
  Preset 4 - Bosphorus 4K
NAS Parallel Benchmarks:
  SP.B
  SP.C
Pennant
Xcompact3d Incompact3d
OpenFOAM
NAS Parallel Benchmarks
Liquid-DSP
Facebook RocksDB
OpenSSL
Xcompact3d Incompact3d
Aircrack-ng
Blender
Helsing
ASKAP
C-Ray
Tachyon
John The Ripper
Embree
Coremark
RELION
m-queens
Liquid-DSP
ASKAP
ASTC Encoder
toyBrot Fractal Generator
Primesieve
NAS Parallel Benchmarks
toyBrot Fractal Generator
oneDNN
John The Ripper
toyBrot Fractal Generator
Algebraic Multi-Grid Benchmark
asmFish
NAS Parallel Benchmarks
NAMD
ACES DGEMM
Stockfish
Xcompact3d Incompact3d
LULESH
Blender
Chaos Group V-RAY
rays1bench
Blender
WRF
KTX-Software toktx
Embree
Rodinia
Liquid-DSP
NAS Parallel Benchmarks
Xmrig
GraphicsMagick
Embree
Xmrig
Blender
GROMACS
Embree
TensorFlow Lite
Embree
TensorFlow Lite
7-Zip Compression
NAS Parallel Benchmarks:
  FT.C
  CG.C
GraphicsMagick
toyBrot Fractal Generator
ASKAP
TensorFlow Lite
LuxCoreRender
Embree
Intel Open Image Denoise
NAS Parallel Benchmarks
TensorFlow Lite:
  Mobilenet Quant
  SqueezeNet
Blender
POV-Ray
ebizzy
Appleseed
Intel Open Image Denoise
NWChem
Intel Open Image Denoise
Pennant
oneDNN:
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
OpenFOAM
oneDNN
Timed LLVM Compilation
oneDNN:
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
LuxCoreRender
Tungsten Renderer
oneDNN
LAMMPS Molecular Dynamics Simulator
SVT-HEVC
CloverLeaf
LuxCoreRender
Timed Node.js Compilation
Quantum ESPRESSO
LAMMPS Molecular Dynamics Simulator
GraphicsMagick
ASKAP
Timed Linux Kernel Compilation
Basis Universal
oneDNN
KeyDB
Kvazaar
Facebook RocksDB
ONNX Runtime
Timed FFmpeg Compilation
Appleseed
oneDNN
Timed LLVM Compilation
ASKAP
oneDNN
NAS Parallel Benchmarks
oneDNN
Rodinia
dav1d
MariaDB:
  256
  512
Basis Universal
KTX-Software toktx
OpenVKL
GraphicsMagick
miniFE
oneDNN
Timed ImageMagick Compilation
oneDNN
Timed Godot Game Engine Compilation
PlaidML
Build2
Timed Mesa Compilation
GraphicsMagick
KTX-Software toktx
Appleseed
ONNX Runtime
Rodinia
Kvazaar
oneDNN
GraphicsMagick
dav1d
Tungsten Renderer
TensorFlow Lite
x265
oneDNN:
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Timed PHP Compilation
SVT-HEVC
oneDNN
ONNX Runtime
PlaidML
Timed GDB GNU Debugger Compilation
ASKAP
oneDNN:
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  IP Shapes 3D - f32 - CPU
PlaidML
ONNX Runtime
SVT-VP9
Tungsten Renderer
WebP2 Image Encode
libavif avifenc
WebP2 Image Encode:
  Quality 95, Compression Effort 7
  Quality 75, Compression Effort 7
oneDNN:
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
ASKAP
SVT-VP9
Kripke
WebP2 Image Encode
SVT-VP9
SVT-HEVC
OpenVKL
Facebook RocksDB
TTSIOD 3D Renderer
OpenVKL
Timed Wasmer Compilation
Timed Apache Compilation
ASTC Encoder:
  Exhaustive
  Thorough
  Medium
VP9 libvpx Encoding:
  Speed 5 - Bosphorus 1080p
  Speed 0 - Bosphorus 1080p
  Speed 5 - Bosphorus 4K
  Speed 0 - Bosphorus 4K
srsRAN:
  5G PHY_DL_NR Test 270 PRB SISO 256-QAM:
    UE Mb/s
    eNb Mb/s
  5G PHY_DL_NR Test 52 PRB SISO 64-QAM:
    UE Mb/s
    eNb Mb/s
  4G PHY_DL_Test 100 PRB SISO 256-QAM:
    UE Mb/s
    eNb Mb/s
  4G PHY_DL_Test 100 PRB MIMO 256-QAM:
    UE Mb/s
    eNb Mb/s
  4G PHY_DL_Test 100 PRB SISO 64-QAM:
    UE Mb/s
    eNb Mb/s
  4G PHY_DL_Test 100 PRB MIMO 64-QAM:
    UE Mb/s
    eNb Mb/s
  OFDM_Test:
    Samples / Second
ONNX Runtime
Cpuminer-Opt:
  LBC, LBRY Credits
  Myriad-Groestl
  Skeincoin
  Blake-2 S
  Deepcoin
  x25x
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
YafaRay
LuxCoreRender:
  Rainbow Colors and Prism - CPU
  LuxCore Benchmark - CPU
Rodinia