AMD EPYC, Intel Xeon Server CPUs June 2021

Benchmarks for a future article by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2106158-IB-SC960487326
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 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 2 Tests
Chess Test Suite 3 Tests
Timed Code Compilation 8 Tests
C/C++ Compiler Tests 17 Tests
CPU Massive 25 Tests
Creator Workloads 22 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 4 Tests
Encoding 4 Tests
Fortran Tests 5 Tests
Game Development 7 Tests
HPC - High Performance Computing 17 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Linear Algebra 2 Tests
Machine Learning 3 Tests
Molecular Dynamics 8 Tests
MPI Benchmarks 6 Tests
Multi-Core 42 Tests
NVIDIA GPU Compute 6 Tests
Intel oneAPI 4 Tests
OpenMPI Tests 12 Tests
Programmer / Developer System Benchmarks 10 Tests
Python Tests 6 Tests
Raytracing 4 Tests
Renderers 8 Tests
Scientific Computing 10 Tests
Server CPU Tests 19 Tests
Texture Compression 3 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 3 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock 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
EPYC 7343
June 07 2021
  16 Hours, 5 Minutes
2 x EPYC 7343
June 08 2021
  11 Hours, 15 Minutes
EPYC 7443
June 10 2021
  13 Hours, 50 Minutes
2 x EPYC 7443
June 11 2021
  9 Hours, 8 Minutes
EPYC 7713
June 04 2021
  11 Hours, 17 Minutes
2 x EPYC 7713
June 06 2021
  10 Hours, 36 Minutes
EPYC 7763
June 12 2021
  10 Hours, 40 Minutes
2 x EPYC 7763
June 14 2021
  9 Hours, 31 Minutes
Xeon Platinum 8380
June 02 2021
  12 Hours, 10 Minutes
2 x Xeon Platinum 8380
June 01 2021
  9 Hours, 18 Minutes
Invert Hiding All Results Option
  11 Hours, 23 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):


AMD EPYC, Intel Xeon Server CPUs June 2021 ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380AMD EPYC 7343 16-Core @ 3.20GHz (16 Cores / 32 Threads)AMD DAYTONA_X (RYM1001D BIOS)AMD Starship/Matisse252GB7682GB INTEL SSDPF2KX076TZllvmpipe2 x Mellanox MT27710Ubuntu 21.045.13.0-051300rc4-generic (x86_64) 20210530X Server 1.20.114.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits)GCC 10.3.0ext41920x10802 x AMD EPYC 7343 16-Core @ 3.20GHz (32 Cores / 64 Threads)504GBAMD EPYC 7443 24-Core @ 2.85GHz (24 Cores / 48 Threads)252GB2 x AMD EPYC 7443 24-Core @ 2.85GHz (48 Cores / 96 Threads)504GBAMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads)252GB2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads)504GBAMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads)252GB2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)504GBIntel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 0998252GB2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)504GBOpenBenchmarking.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- EPYC 7343: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- 2 x EPYC 7343: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- EPYC 7443: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- 2 x EPYC 7443: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- EPYC 7713: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- 2 x EPYC 7713: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- EPYC 7763: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- 2 x EPYC 7763: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119- Xeon Platinum 8380: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270- 2 x Xeon Platinum 8380: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python Details- Python 3.9.5Security Details- EPYC 7343: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- 2 x EPYC 7343: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7443: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- 2 x EPYC 7443: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7713: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- 2 x EPYC 7713: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7763: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- 2 x EPYC 7763: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8380: 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- 2 x Xeon Platinum 8380: 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

EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380Logarithmic Result OverviewPhoronix Test SuiteCpuminer-OptACES DGEMMStockfishAircrack-ngC-RayasmFishASTC EncoderJohn The Ripperm-queensTachyonPennanttoyBrot Fractal GeneratorNAMDrays1benchPrimesieveFacebook RocksDBIntel Open Image DenoiseBlenderASKAPoneDNNLiquid-DSPCoremarkGROMACSGraphicsMagickEmbreeHelsing7-Zip CompressionXmrigLULESHLuxCoreRenderPOV-RayNAS Parallel BenchmarksRodiniaTimed Node.js CompilationNWChemWRFXcompact3d Incompact3dLAMMPS Molecular Dynamics SimulatorSVT-AV1TensorFlow LiteOpenFOAMTimed LLVM CompilationAppleseedTimed Linux Kernel CompilationSVT-HEVCBasis UniversalAlgebraic Multi-Grid BenchmarkKTX-Software toktxKvazaarTimed FFmpeg CompilationBRL-CADOpenVKLPlaidMLdav1dTimed Mesa CompilationTimed Godot Game Engine CompilationTimed ImageMagick CompilationTimed Wasmer Compilation

EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380Logarithmic Per Watt Result OverviewPhoronix Test SuiteCpuminer-OptSVT-AV1ACES DGEMMrays1benchASKAPdav1dEmbreeStockfishXmrigCoremark7-Zip CompressionLuxCoreRenderFacebook RocksDBasmFishSVT-HEVCAircrack-ngKvazaarJohn The RipperLiquid-DSPGraphicsMagickOpenVKLLAMMPS Molecular Dynamics SimulatorGROMACSIntel Open Image DenoiseBRL-CADPlaidMLAlgebraic Multi-Grid BenchmarkNAS Parallel BenchmarksLULESHP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

AMD EPYC, Intel Xeon Server CPUs June 2021 onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUcpuminer-opt: x25xonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUmt-dgemm: Sustained Floating-Point Ratenpb: EP.Dcpuminer-opt: LBC, LBRY Creditsstockfish: Total Timetoybrot: TBBblender: Classroom - CPU-Onlyrocksdb: Rand Readaircrack-ng: c-ray: Total Time - 4K, 16 Rays Per Pixelasmfish: 1024 Hash Memory, 26 Depthtoybrot: C++ Threadsnpb: EP.Cjohn-the-ripper: MD5astcenc: Exhaustiveliquid-dsp: 128 - 256 - 57toybrot: C++ Tasksm-queens: Time To Solveliquid-dsp: 160 - 256 - 57pennant: leblancbigjohn-the-ripper: Blowfishtachyon: Total Timepennant: sedovbigembree: Pathtracer - Crownblender: Barbershop - CPU-Onlyembree: Pathtracer ISPC - Crownnamd: ATPase Simulation - 327,506 Atomsrays1bench: Large Sceneprimesieve: 1e12 Prime Number Generationembree: Pathtracer ISPC - Asian Dragontoybrot: OpenMPtoktx: UASTC 4 + Zstd Compression 19rodinia: OpenMP LavaMDaskap: tConvolve MPI - Degriddingoidn: RT.ldr_alb_nrm.3840x2160oidn: RT.hdr_alb_nrm.3840x2160blender: Pabellon Barcelona - CPU-Onlyoidn: RTLightmap.hdr.4096x4096onednn: Convolution Batch Shapes Auto - f32 - CPUaskap: tConvolve MPI - Griddingxmrig: Monero - 1Mcoremark: CoreMark Size 666 - Iterations Per Secondgraphics-magick: Sharpengromacs: MPI CPU - water_GMX50_bareluxcorerender: DLSC - CPUluxcorerender: Orange Juice - CPUblender: BMW27 - CPU-Onlyrocksdb: Read While Writinghelsing: 14 digitcompress-7zip: Compress Speed Testlulesh: graphics-magick: Enhancednpb: BT.Csvt-hevc: 1 - Bosphorus 1080pnpb: LU.Cblender: Fishy Cat - CPU-Onlyonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUxmrig: Wownero - 1Mv-ray: CPUembree: Pathtracer - Asian Dragontensorflow-lite: Inception ResNet V2povray: Trace Timebuild-llvm: Ninjaluxcorerender: Danish Mood - CPUopenvkl: vklBenchmarkluxcorerender: LuxCore Benchmark - CPUnpb: SP.Cnpb: SP.Bopenfoam: Motorbike 30Mliquid-dsp: 64 - 256 - 57incompact3d: input.i3d 193 Cells Per Directionnwchem: C240 Buckyballbuild-nodejs: Time To Compilelammps: 20k Atomswrf: conus 2.5kmopenfoam: Motorbike 60Mtensorflow-lite: Inception V4svt-av1: Preset 8 - Bosphorus 4Knpb: FT.Cbasis: UASTC Level 3incompact3d: X3D-benchmarking input.i3drodinia: OpenMP CFD Solversvt-av1: Preset 4 - Bosphorus 4Kappleseed: Disney Materiallammps: Rhodopsin Proteinbuild-linux-kernel: Time To Compilenpb: CG.Cnpb: IS.Dtensorflow-lite: SqueezeNetamg: npb: MG.Ckvazaar: Bosphorus 4K - Very Fastbuild-llvm: Unix Makefilesbuild-ffmpeg: Time To Compilebasis: UASTC Level 2brl-cad: VGR Performance Metriccpuminer-opt: Garlicoindav1d: Summer Nature 4Kplaidml: No - Inference - VGG19 - CPUtoktx: UASTC 3plaidml: No - Inference - VGG16 - CPUsvt-hevc: 7 - Bosphorus 1080pbuild-mesa: Time To Compiledav1d: Chimera 1080p 10-bitopenvkl: vklBenchmarkVdbVolumebuild-godot: Time To Compilebuild-imagemagick: Time To Compiletoktx: UASTC 3 + Zstd Compression 19openvkl: vklBenchmarkStructuredVolumebuild-wasmer: Time To Compilecpuminer-opt: Skeincoincpuminer-opt: Deepcoincpuminer-opt: MagiEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801.76480543.831.783615.6969241638.54818574959822521360250.7711339170368979.54734.49350923399213101626.20189466759.001610471000002160334.378107406666718.022633471948.392627.3649921.2675333.7219.38941.15901108.1512.39021.186621271173.392114.46510427.20.620.62275.290.312.627311221712650.0731356.7116722022.3863.265.0387.363656213326.7521236739345.659737567984.3414.9476603.34113.043.1084513477.81874523.6270138571025.248340.4912.512542.7436870.6746716.5739.23102043333333.47496415578.2221.27611.99624803.735263.64154242321.52643155.2831.518792.62778712.8051.972128.60250211.95148.46519753.541894.6310872992352816053570.3226.09374.19931.15118.1882346573677.23309.9518.007.30621.74197.6028.417698.601835733775.73416.98313.0337979227842.34821279019320828.261.065161061.901.0113810.5540393222.221604369201761910695125.95226767248136466.77117.49892794578108703235.02369300030.016220455666671095617.35820800666678.3612766897624.393814.0221537.3366184.9834.41840.59342235.856.26335.64901097691.12259.94720854.51.141.14140.290.571.2035624232.820697.81442185.7225023634.0565.668.6746.015688379162.85020703423367.907638109453.7528.37139874.5762.372.6817721774.83413438.167486697413.897188.6084.384004.5968019.8990510.8143.59203003333318.01224613041.4127.82818.25613171.279152.3697028821.71878574.0018.958405.0966499.7071.99769.17825216.36529.97032439.062849.3776346.8164721275086413.6338.67230.57820.65312.2464022247661.49400.2925.345.04129.78305.0419.200743.221954605754.89112.80010.9569180995637.072437750301531639.581.44584756.921.3047110.7465212386.401212137301567015244177.6715888360797158.96924.30073066534151422389.29266466742.081614559333331522523.842147600000013.173924930534.323220.2852629.2803239.5226.74470.83727156.118.85229.722715258124.47482.54412839.80.840.84195.240.422.0344714495.717437.61046268.8542482813.1494.586.9862.525081422233.0441709729333.161251570079.2520.7976463.0981.262.8468419754.72584333.0559111651318.390253.6673.593483.9136773.0247458.8728.46143093333330.03828434051.2168.34816.23521447.808264.46126063023.48544870.9923.906716.3620609.9562.11895.77295115.64837.46621383.551895.9184986.092084287553096.6129.85295.30924.92214.4853374755119.45397.6222.375.83828.10269.5123.067767.812073010960.95114.65311.6489566217238.244298157289871177.540.8071361521.470.80720114.9733374650.02241120129961331783189.50318820918192231.83812.35913151255476924643.61517266722.34442859566667787412.11628763000006.0939589744817.904210.3954052.1267134.6147.96280.43867314.534.53345.5318786366.61243.73124994.31.541.54102.120.770.90092228113.828086.21998209.2000664855.1907.8711.7534.657420817119.51328648023653.533838138196.3037.28141063.7548.592.7017631611.14651548.290378155510.400149.5005.794896.1471183.8095708.0617.95268876666716.39581172177.5102.42724.81611194.371136.1387003422.62182082.4315.136360.7921048.4282.07954.28530923.15224.24632040.762911.7461531.0168270433385423.7944.85192.96217.36610.38159684710693475.5727.094.37831.43347.7016.828904.482141861648.64711.82710.33310054429036.396640993516732402.650.7862891564.210.81967420.4744924748.97250383149214033775191.94307317781186261.67712.67813300511877714435.73508500022.39872735733333808013.16727382000006.6545419693817.954911.1990253.2405133.1948.05670.45183272.454.93256.4813820367.70248.07720446.81.431.42105.650.700.94538121791.228145.21982329.0905694945.1208.3111.8035.538778202128.07330069018128.943880129163.4034.64136132.3350.571.6381937011.24366462.893061275810.582161.8286.415826.8851957.1690434.6821.02259070000022.14948522187.6110.97126.01117010.988205.3067285955.59760492.2615.703608.2285366.7474.78862.01768822.54326.32224472.582531.7651560.199486036757387.1436.83216.84018.90610.84566119214410521.0727.294.45031.97320.2119.002952.432310199851.27912.88810.57411127591540.956628793658632447.830.7894853970.770.73164731.4332359272.13519340261240741396947.87610980307369512.5736.57024384243541598826.32953533312.5419515300000043956.84752296333333.6226821845069.92195.67451589.878076.6582.83410.26463505.322.71466.8485486639.49425.92740240.42.252.2467.131.090.63100042695.950909.23001332.2205847838.51812.2318.1623.7014966330145.56345246735233.2531336237936.8249.81261304.6734.491.01534641905.470.10224509947.739106.5217.715717.95114285.74142813.7216.08283063333311.21016462173.977.68931.2668587.36792.6155312856.827116003.8411.575299.0869966.0494.80751.09540828.05219.55944800.924340.4350330.71913804333101537.0551.47181.89415.1549.043312083428307571.2430.423.96434.46320.6316.9631003.002264515754.62211.58610.03410523016242.29310862991067735547.670.7162281717.400.76265423.5207095411.58252517170298174689081.03345334994208055.63011.19715962779068434941.83576200020.07063033166667724211.94030409000005.95106310927416.12299.94006262.7823111.9257.57910.38327293.344.40265.4312732260.73741.51622987.81.661.6693.990.820.84986324224.031822.02113523.1746775835.6849.5313.2631.979288689115.85333472918991.1341052136092.4040.13143783.0146.011.6062742371.85630269.42315848749.730145.5727.506368.2852123.9091716.9519.78292693333321.99355192036.4101.28029.72316479.889204.5864464361.28162384.3714.842602.9665736.5165.05156.03643124.88224.35224861.342563.8051608.3101263300058310.4540.27203.21817.90110.57875193414683558.1932.224.35237.71342.8018.293980.822376866748.65412.61210.64411268822940.584625381678172615.920.7094664322.910.70616037.70684310643.55513033306393152352541.65681491345414028.8445.79629842699936399431.171089366710.5884582450000038916.22359045000003.3121251873809.01945.172542110.736964.18100.43000.22546555.932.42268.7381432735.37823.46344826.52.552.5257.711.250.57895247724.756659.13220418.05648188210.17613.5520.7421.3014789793108.81949587836956.2081449256826.3556.28287566.1030.710.85405047971.371.00043949537.29998.7188.546118.65115068.83145772.3115.33309133333311.12039261914.473.61335.0918323.11989.8352747262.071120465.5011.339297.6757306.1405.05047.81937530.95518.62949508.634511.0451986.71926452000101849.5555.84176.96614.9189.114313310328680605.3832.363.96935.92342.9816.8391130.162332644251.44111.69110.24610996490741.57912188481129186083.020.3103621022.320.23432714.6961384593.842737809487944813486142.20182180961105477.35221.64589220384134394334.33530566732.490315652666671372622.128157930000011.328996055326.873623.8430036.0739195.1644.16890.51889184.567.16658.291914057102.03071.9919239.591.791.78164.010.851.4595210580.914658.21206142.6968363705.0175.508.9551.056676556161.64720159618779.645641117333.4723.7098453.5574.511.4825623539.93534742.6100102606015.515208.6514.426414.5037645.4150133.5823.49165406666724.04323203085.1142.50922.68218356.463224.58117846321.80157275.0822.870554.9387616.2111.85977.52192520.84132.01222890.252333.5680455.7108441166756287.5327.57256.63022.31614.93042332415618404.2731.066.01336.97290.3621.794775.382909215556.58014.36910.38710502396337.683407502335831346.630.1906282725.030.22863228.1467338890.34402726180945380692471.11373831966211019.99011.00817112162869927939.021020000016.64213279266667788311.30130865333334.70761011886913.682514.4137964.7709103.8775.49670.27064346.313.693107.9025728154.91739.06918222.52.992.9887.631.441.3971720662.026504.22365407.6242146729.0639.4114.3328.24917026081.46435514035311.8451125198052.3837.49188790.1444.450.91508642770.86632883.57235727509.257127.9936.978206.8992499.87123538.1414.30304733333311.05813461846.890.57035.9899822.727103.6166696757.416100812.5415.513291.4161994.7094.73457.39698331.56121.62740188.843086.2447974.62082103333118831.5238.71190.68316.42611.415241158741269532.5733.434.65838.51313.9318.712861.392914304448.06811.9629.11110492207037.688774163750613651.80OpenBenchmarking.org

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.39710.79421.19131.58841.9855SE +/- 0.003849, N = 9SE +/- 0.003377, N = 9SE +/- 0.003946, N = 9SE +/- 0.007751, N = 15SE +/- 0.002979, N = 9SE +/- 0.011037, N = 15SE +/- 0.002657, N = 9SE +/- 0.005545, N = 10SE +/- 0.002283, N = 15SE +/- 0.000612, N = 91.7648001.0651601.4458400.8071360.7862890.7894850.7162280.7094660.3103620.190628MIN: 1.63MIN: 0.95MIN: 1.26MIN: 0.66MIN: 0.72MIN: 0.49MIN: 0.68MIN: 0.591. (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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 1.75 / Avg: 1.76 / Max: 1.78Min: 1.05 / Avg: 1.07 / Max: 1.09Min: 1.42 / Avg: 1.45 / Max: 1.46Min: 0.77 / Avg: 0.81 / Max: 0.88Min: 0.77 / Avg: 0.79 / Max: 0.81Min: 0.71 / Avg: 0.79 / Max: 0.86Min: 0.71 / Avg: 0.72 / Max: 0.73Min: 0.67 / Avg: 0.71 / Max: 0.74Min: 0.3 / Avg: 0.31 / Max: 0.34Min: 0.19 / Avg: 0.19 / Max: 0.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: x25xEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83809001800270036004500SE +/- 0.29, N = 3SE +/- 1.19, N = 3SE +/- 4.49, N = 3SE +/- 1.74, N = 3SE +/- 27.65, N = 15SE +/- 35.98, N = 3SE +/- 13.85, N = 15SE +/- 42.17, N = 6SE +/- 14.01, N = 3SE +/- 50.45, N = 15543.831061.90756.921521.471564.213970.771717.404322.911022.322725.031. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: x25xEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808001600240032004000Min: 543.39 / Avg: 543.83 / Max: 544.39Min: 1060.3 / Avg: 1061.9 / Max: 1064.23Min: 750.61 / Avg: 756.92 / Max: 765.61Min: 1518.74 / Avg: 1521.47 / Max: 1524.69Min: 1443.75 / Avg: 1564.21 / Max: 1819.49Min: 3911.48 / Avg: 3970.77 / Max: 4035.73Min: 1650.53 / Avg: 1717.4 / Max: 1819.28Min: 4225.15 / Avg: 4322.91 / Max: 4494.57Min: 994.34 / Avg: 1022.32 / Max: 1037.57Min: 2151.25 / Avg: 2725.03 / Max: 2933.541. (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: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.40130.80261.20391.60522.0065SE +/- 0.001094, N = 4SE +/- 0.005231, N = 4SE +/- 0.008517, N = 4SE +/- 0.002298, N = 4SE +/- 0.000581, N = 4SE +/- 0.002628, N = 4SE +/- 0.002824, N = 4SE +/- 0.005550, N = 4SE +/- 0.000310, N = 4SE +/- 0.001610, N = 41.7836101.0113801.3047100.8072010.8196740.7316470.7626540.7061600.2343270.228632MIN: 1.68MIN: 0.91MIN: 1.19MIN: 0.73MIN: 0.76MIN: 0.65MIN: 0.71MIN: 0.611. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 1.78 / Avg: 1.78 / Max: 1.79Min: 1 / Avg: 1.01 / Max: 1.03Min: 1.29 / Avg: 1.3 / Max: 1.33Min: 0.8 / Avg: 0.81 / Max: 0.81Min: 0.82 / Avg: 0.82 / Max: 0.82Min: 0.73 / Avg: 0.73 / Max: 0.74Min: 0.76 / Avg: 0.76 / Max: 0.77Min: 0.7 / Avg: 0.71 / Max: 0.72Min: 0.23 / Avg: 0.23 / Max: 0.24Min: 0.22 / Avg: 0.23 / Max: 0.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 RateEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380918273645SE +/- 0.020317, N = 3SE +/- 0.009641, N = 3SE +/- 0.062123, N = 3SE +/- 0.139231, N = 4SE +/- 0.097522, N = 5SE +/- 0.199013, N = 15SE +/- 0.215679, N = 6SE +/- 0.310301, N = 15SE +/- 0.032828, N = 4SE +/- 0.078306, N = 65.69692410.55403910.74652114.97333720.47449231.43323523.52070937.70684314.69613828.1467331. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240Min: 5.66 / Avg: 5.7 / Max: 5.73Min: 10.54 / Avg: 10.55 / Max: 10.57Min: 10.66 / Avg: 10.75 / Max: 10.87Min: 14.61 / Avg: 14.97 / Max: 15.25Min: 20.2 / Avg: 20.47 / Max: 20.73Min: 29.86 / Avg: 31.43 / Max: 32.48Min: 22.94 / Avg: 23.52 / Max: 24.43Min: 35.53 / Avg: 37.71 / Max: 39.52Min: 14.62 / Avg: 14.7 / Max: 14.78Min: 27.93 / Avg: 28.15 / Max: 28.441. (CC) gcc options: -O3 -march=native -fopenmp

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.DEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802K4K6K8K10KSE +/- 7.20, N = 3SE +/- 32.13, N = 6SE +/- 2.20, N = 3SE +/- 87.99, N = 12SE +/- 55.79, N = 15SE +/- 150.39, N = 15SE +/- 3.87, N = 3SE +/- 109.94, N = 4SE +/- 12.97, N = 3SE +/- 95.83, N = 51638.543222.222386.404650.024748.979272.135411.5810643.554593.848890.341. (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
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802K4K6K8K10KMin: 1629.66 / Avg: 1638.54 / Max: 1652.79Min: 3063.29 / Avg: 3222.22 / Max: 3264.79Min: 2383.56 / Avg: 2386.4 / Max: 2390.73Min: 3719.96 / Avg: 4650.02 / Max: 4781.56Min: 4152.95 / Avg: 4748.97 / Max: 4886.86Min: 8219.76 / Avg: 9272.13 / Max: 9704.84Min: 5403.83 / Avg: 5411.58 / Max: 5415.52Min: 10318.62 / Avg: 10643.55 / Max: 10792.43Min: 4568.5 / Avg: 4593.84 / Max: 4611.33Min: 8529.39 / Avg: 8890.34 / Max: 9056.451. (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

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 CreditsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380110K220K330K440K550KSE +/- 927.48, N = 3SE +/- 1462.70, N = 7SE +/- 1348.66, N = 3SE +/- 1113.93, N = 3SE +/- 2811.89, N = 3SE +/- 7474.68, N = 3SE +/- 1388.14, N = 3SE +/- 4432.38, N = 3SE +/- 7613.62, N = 12SE +/- 30611.01, N = 12818571604361212132411202503835193402525175130332737804027261. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: LBC, LBRY CreditsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838090K180K270K360K450KMin: 80020 / Avg: 81856.67 / Max: 83000Min: 155520 / Avg: 160435.71 / Max: 167130Min: 118570 / Avg: 121213.33 / Max: 123000Min: 239120 / Avg: 241120 / Max: 242970Min: 245790 / Avg: 250383.33 / Max: 255490Min: 509030 / Avg: 519340 / Max: 533870Min: 249750 / Avg: 252516.67 / Max: 254100Min: 506670 / Avg: 513033.33 / Max: 521560Min: 197030 / Avg: 273780 / Max: 291550Min: 223880 / Avg: 402725.83 / Max: 5329501. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070M140M210M280M350MSE +/- 568419.83, N = 3SE +/- 845874.18, N = 3SE +/- 781313.94, N = 15SE +/- 1572920.31, N = 4SE +/- 985441.45, N = 14SE +/- 2267477.82, N = 15SE +/- 1590426.12, N = 15SE +/- 2199817.87, N = 15SE +/- 570049.11, N = 3SE +/- 1599896.72, N = 349598225920176197301567012996133114921403326124074117029817430639315294879448180945380-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050M100M150M200M250MMin: 48485340 / Avg: 49598224.67 / Max: 50355712Min: 90417716 / Avg: 92017619 / Max: 93293745Min: 66269217 / Avg: 73015669.6 / Max: 78961696Min: 128305175 / Avg: 129961331 / Max: 134679237Min: 143995387 / Avg: 149214032.5 / Max: 155468660Min: 248492200 / Avg: 261240741.33 / Max: 276826862Min: 164514328 / Avg: 170298173.8 / Max: 185066844Min: 295039768 / Avg: 306393151.93 / Max: 320559307Min: 93759974 / Avg: 94879448.33 / Max: 95626137Min: 177771047 / Avg: 180945380.33 / Max: 1828814231. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

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: TBBEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805K10K15K20K25KSE +/- 145.36, N = 3SE +/- 45.80, N = 5SE +/- 98.87, N = 15SE +/- 73.46, N = 15SE +/- 59.24, N = 6SE +/- 25.31, N = 8SE +/- 38.66, N = 6SE +/- 29.34, N = 9SE +/- 115.12, N = 8SE +/- 55.68, N = 9213601069515244783177513969689035251348669241. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804K8K12K16K20KMin: 21210 / Avg: 21360.33 / Max: 21651Min: 10623 / Avg: 10695 / Max: 10852Min: 14936 / Avg: 15244.2 / Max: 16360Min: 7497 / Avg: 7830.6 / Max: 8578Min: 7598 / Avg: 7750.67 / Max: 8013Min: 3857 / Avg: 3969 / Max: 4054Min: 6705 / Avg: 6890.33 / Max: 6974Min: 3388 / Avg: 3525.11 / Max: 3663Min: 13151 / Avg: 13486.25 / Max: 14122Min: 6620 / Avg: 6923.89 / Max: 72341. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050100150200250SE +/- 0.16, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.25, N = 3SE +/- 0.11, N = 3250.77125.95177.6789.5091.9447.8781.0341.65142.2071.11
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050100150200250Min: 250.56 / Avg: 250.77 / Max: 251.08Min: 125.66 / Avg: 125.95 / Max: 126.24Min: 177.43 / Avg: 177.67 / Max: 177.97Min: 89.45 / Avg: 89.5 / Max: 89.55Min: 91.88 / Avg: 91.94 / Max: 92.06Min: 47.73 / Avg: 47.87 / Max: 48.05Min: 80.92 / Avg: 81.03 / Max: 81.09Min: 41.45 / Avg: 41.65 / Max: 41.84Min: 141.94 / Avg: 142.2 / Max: 142.7Min: 70.95 / Avg: 71.11 / Max: 71.31

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 ReadEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380150M300M450M600M750MSE +/- 221538.78, N = 3SE +/- 185072.14, N = 3SE +/- 496926.24, N = 3SE +/- 304242.36, N = 3SE +/- 475202.04, N = 3SE +/- 1833762.88, N = 3SE +/- 438896.45, N = 3SE +/- 1168980.04, N = 3SE +/- 1359270.00, N = 3SE +/- 1003430.17, N = 31133917032267672481588836073188209183073177816109803073453349946814913451821809613738319661. (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 ReadEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380120M240M360M480M600MMin: 113101862 / Avg: 113391703.33 / Max: 113826852Min: 226570499 / Avg: 226767247.67 / Max: 227137141Min: 158324103 / Avg: 158883606.67 / Max: 159874712Min: 318500126 / Avg: 318820918 / Max: 319429097Min: 306367401 / Avg: 307317780.67 / Max: 307798870Min: 607867108 / Avg: 610980306.67 / Max: 614215910Min: 344828704 / Avg: 345334994.33 / Max: 346209141Min: 680171119 / Avg: 681491344.67 / Max: 683822474Min: 179565210 / Avg: 182180961.33 / Max: 184130108Min: 372599347 / Avg: 373831966 / Max: 3758198091. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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 1.5.2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838090K180K270K360K450KSE +/- 93.43, N = 3SE +/- 40.09, N = 3SE +/- 75.23, N = 3SE +/- 78.39, N = 3SE +/- 92.12, N = 3SE +/- 17.10, N = 3SE +/- 167.50, N = 3SE +/- 128.13, N = 3SE +/- 128.50, N = 3SE +/- 353.02, N = 368979.55136466.7797158.97192231.84186261.68369512.57208055.63414028.84105477.35211019.991. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070K140K210K280K350KMin: 68835.95 / Avg: 68979.55 / Max: 69154.91Min: 136388.58 / Avg: 136466.77 / Max: 136521.22Min: 97044.48 / Avg: 97158.97 / Max: 97300.76Min: 192103.58 / Avg: 192231.84 / Max: 192374.06Min: 186077.5 / Avg: 186261.68 / Max: 186357.64Min: 369484.88 / Avg: 369512.57 / Max: 369543.78Min: 207848.47 / Avg: 208055.63 / Max: 208387.2Min: 413773.5 / Avg: 414028.84 / Max: 414175.25Min: 105232.53 / Avg: 105477.35 / Max: 105667.47Min: 210319.34 / Avg: 211019.99 / Max: 211445.781. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

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 PixelEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240SE +/- 0.008, N = 3SE +/- 0.007, N = 3SE +/- 0.015, N = 3SE +/- 0.031, N = 4SE +/- 0.007, N = 4SE +/- 0.033, N = 6SE +/- 0.016, N = 4SE +/- 0.049, N = 7SE +/- 0.167, N = 3SE +/- 0.011, N = 534.49317.49824.30012.35912.6786.57011.1975.79621.64511.0081. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 34.48 / Avg: 34.49 / Max: 34.51Min: 17.48 / Avg: 17.5 / Max: 17.51Min: 24.27 / Avg: 24.3 / Max: 24.32Min: 12.31 / Avg: 12.36 / Max: 12.44Min: 12.66 / Avg: 12.68 / Max: 12.7Min: 6.47 / Avg: 6.57 / Max: 6.69Min: 11.17 / Avg: 11.2 / Max: 11.24Min: 5.6 / Avg: 5.8 / Max: 5.96Min: 21.31 / Avg: 21.64 / Max: 21.82Min: 10.98 / Avg: 11.01 / Max: 11.041. (CC) gcc options: -lm -lpthread -O3

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 DepthEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060M120M180M240M300MSE +/- 256508.93, N = 3SE +/- 796536.99, N = 3SE +/- 410708.26, N = 3SE +/- 1764787.58, N = 3SE +/- 1252738.91, N = 6SE +/- 1424672.62, N = 3SE +/- 1498279.20, N = 3SE +/- 4193004.96, N = 3SE +/- 767934.53, N = 3SE +/- 1594885.41, N = 1250923399927945787306653413151255413300511824384243515962779029842699989220384171121628
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050M100M150M200M250MMin: 50422213 / Avg: 50923399 / Max: 51268860Min: 91565163 / Avg: 92794578 / Max: 94286678Min: 72558384 / Avg: 73066534 / Max: 73879520Min: 128637931 / Avg: 131512554 / Max: 134723515Min: 130073913 / Avg: 133005117.67 / Max: 138863245Min: 241013819 / Avg: 243842435.33 / Max: 245553852Min: 156736600 / Avg: 159627789.67 / Max: 161755505Min: 293087386 / Avg: 298426999.33 / Max: 306696830Min: 87725441 / Avg: 89220384.33 / Max: 90272862Min: 166326779 / Avg: 171121627.58 / Max: 182137078

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++ ThreadsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805K10K15K20K25KSE +/- 9.21, N = 3SE +/- 20.75, N = 5SE +/- 18.89, N = 4SE +/- 8.19, N = 6SE +/- 16.30, N = 6SE +/- 18.85, N = 8SE +/- 11.27, N = 6SE +/- 13.90, N = 9SE +/- 27.98, N = 4SE +/- 17.11, N = 6213101087015142769277714159684336391343969921. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ ThreadsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804K8K12K16K20KMin: 21297 / Avg: 21310.33 / Max: 21328Min: 10805 / Avg: 10870.4 / Max: 10928Min: 15116 / Avg: 15142 / Max: 15198Min: 7663 / Avg: 7692.33 / Max: 7711Min: 7721 / Avg: 7771.33 / Max: 7820Min: 4092 / Avg: 4159.38 / Max: 4251Min: 6816 / Avg: 6842.5 / Max: 6888Min: 3586 / Avg: 3638.67 / Max: 3706Min: 13377 / Avg: 13438.75 / Max: 13509Min: 6939 / Avg: 6992.17 / Max: 70501. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802K4K6K8K10KSE +/- 8.44, N = 7SE +/- 24.46, N = 10SE +/- 5.74, N = 8SE +/- 31.65, N = 15SE +/- 44.58, N = 15SE +/- 73.64, N = 8SE +/- 77.82, N = 15SE +/- 82.93, N = 8SE +/- 32.20, N = 11SE +/- 69.57, N = 151626.203235.022389.294643.614435.738826.324941.839431.174334.337939.021. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838016003200480064008000Min: 1578.99 / Avg: 1626.2 / Max: 1645.49Min: 3018.71 / Avg: 3235.02 / Max: 3286.06Min: 2357.97 / Avg: 2389.29 / Max: 2410.6Min: 4314.93 / Avg: 4643.61 / Max: 4777.9Min: 4195.54 / Avg: 4435.73 / Max: 4783.79Min: 8537.14 / Avg: 8826.32 / Max: 9101.83Min: 4248.25 / Avg: 4941.83 / Max: 5264.85Min: 9254.8 / Avg: 9431.17 / Max: 9822.99Min: 4117.06 / Avg: 4334.33 / Max: 4467.62Min: 7578.26 / Avg: 7939.02 / Max: 8414.841. (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

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: MD5EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802M4M6M8M10MSE +/- 333.33, N = 3SE +/- 4358.90, N = 3SE +/- 4333.33, N = 3SE +/- 10333.33, N = 3SE +/- 14189.20, N = 3SE +/- 95237.48, N = 6SE +/- 5196.15, N = 3SE +/- 13908.43, N = 3SE +/- 15762.12, N = 3SE +/- 14502.87, N = 31894667369300026646675172667508500095353335762000108936675305667102000001. (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: MD5EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802M4M6M8M10MMin: 1894000 / Avg: 1894666.67 / Max: 1895000Min: 3685000 / Avg: 3693000 / Max: 3700000Min: 2656000 / Avg: 2664666.67 / Max: 2669000Min: 5153000 / Avg: 5172666.67 / Max: 5188000Min: 5067000 / Avg: 5085000 / Max: 5113000Min: 9111000 / Avg: 9535333.33 / Max: 9790000Min: 5753000 / Avg: 5762000 / Max: 5771000Min: 10866000 / Avg: 10893666.67 / Max: 10910000Min: 5287000 / Avg: 5305666.67 / Max: 5337000Min: 10185000 / Avg: 10200000 / Max: 102290001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

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: ExhaustiveEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801326395265SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.05, N = 3SE +/- 0.01, N = 359.0030.0242.0822.3422.4012.5420.0710.5932.4916.641. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ExhaustiveEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801224364860Min: 58.98 / Avg: 59 / Max: 59.02Min: 29.95 / Avg: 30.02 / Max: 30.1Min: 42.06 / Avg: 42.08 / Max: 42.1Min: 22.29 / Avg: 22.34 / Max: 22.38Min: 22.38 / Avg: 22.4 / Max: 22.42Min: 12.48 / Avg: 12.54 / Max: 12.65Min: 20.04 / Avg: 20.07 / Max: 20.09Min: 10.58 / Avg: 10.59 / Max: 10.6Min: 32.4 / Avg: 32.49 / Max: 32.59Min: 16.63 / Avg: 16.64 / Max: 16.661. (CXX) g++ options: -O3 -flto -pthread

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: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801200M2400M3600M4800M6000MSE +/- 1135781.67, N = 3SE +/- 3233848.76, N = 3SE +/- 1614861.54, N = 3SE +/- 2669165.50, N = 3SE +/- 1534419.90, N = 3SE +/- 3326158.95, N = 3SE +/- 2979000.58, N = 3SE +/- 7574518.69, N = 3SE +/- 3090487.20, N = 3SE +/- 4603018.33, N = 310471000002045566667145593333328595666672735733333515300000030331666675824500000156526666732792666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801000M2000M3000M4000M5000MMin: 1045000000 / Avg: 1047100000 / Max: 1048900000Min: 2039900000 / Avg: 2045566666.67 / Max: 2051100000Min: 1453800000 / Avg: 1455933333.33 / Max: 1459100000Min: 2856700000 / Avg: 2859566666.67 / Max: 2864900000Min: 2733200000 / Avg: 2735733333.33 / Max: 2738500000Min: 5148000000 / Avg: 5153000000 / Max: 5159300000Min: 3027300000 / Avg: 3033166666.67 / Max: 3037000000Min: 5814300000 / Avg: 5824500000 / Max: 5839300000Min: 1560800000 / Avg: 1565266666.67 / Max: 1571200000Min: 3273700000 / Avg: 3279266666.67 / Max: 32884000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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++ TasksEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805K10K15K20K25KSE +/- 23.30, N = 3SE +/- 31.35, N = 5SE +/- 14.71, N = 4SE +/- 13.31, N = 6SE +/- 25.58, N = 6SE +/- 11.75, N = 8SE +/- 35.34, N = 6SE +/- 16.02, N = 8SE +/- 31.23, N = 4SE +/- 27.45, N = 6216031095615225787480804395724238911372678831. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ TasksEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804K8K12K16K20KMin: 21570 / Avg: 21603 / Max: 21648Min: 10883 / Avg: 10956 / Max: 11061Min: 15201 / Avg: 15225.25 / Max: 15267Min: 7819 / Avg: 7873.5 / Max: 7914Min: 8012 / Avg: 8080.17 / Max: 8186Min: 4369 / Avg: 4395.13 / Max: 4466Min: 7147 / Avg: 7241.5 / Max: 7362Min: 3813 / Avg: 3890.5 / Max: 3944Min: 13656 / Avg: 13726 / Max: 13794Min: 7813 / Avg: 7882.5 / Max: 80041. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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 SolveEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240SE +/- 0.014, N = 3SE +/- 0.038, N = 3SE +/- 0.013, N = 3SE +/- 0.016, N = 4SE +/- 0.034, N = 4SE +/- 0.021, N = 6SE +/- 0.017, N = 4SE +/- 0.016, N = 7SE +/- 0.039, N = 3SE +/- 0.027, N = 534.37817.35823.84212.11613.1676.84711.9406.22322.12811.3011. (CXX) g++ options: -fopenmp -O2 -march=native
OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 34.35 / Avg: 34.38 / Max: 34.39Min: 17.29 / Avg: 17.36 / Max: 17.42Min: 23.82 / Avg: 23.84 / Max: 23.86Min: 12.1 / Avg: 12.12 / Max: 12.17Min: 13.12 / Avg: 13.17 / Max: 13.26Min: 6.79 / Avg: 6.85 / Max: 6.94Min: 11.9 / Avg: 11.94 / Max: 11.98Min: 6.16 / Avg: 6.22 / Max: 6.29Min: 22.06 / Avg: 22.13 / Max: 22.2Min: 11.22 / Avg: 11.3 / Max: 11.381. (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: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801300M2600M3900M5200M6500MSE +/- 5366666.67, N = 3SE +/- 6901771.11, N = 3SE +/- 1452583.90, N = 3SE +/- 1311487.70, N = 3SE +/- 1205542.75, N = 3SE +/- 3598302.07, N = 3SE +/- 709459.89, N = 3SE +/- 4064890.32, N = 3SE +/- 2451530.13, N = 3SE +/- 284800.12, N = 310740666672080066667147600000028763000002738200000522963333330409000005904500000157930000030865333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 160 - Buffer Length: 256 - Filter Length: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801000M2000M3000M4000M5000MMin: 1068700000 / Avg: 1074066666.67 / Max: 1084800000Min: 2070600000 / Avg: 2080066666.67 / Max: 2093500000Min: 1473100000 / Avg: 1476000000 / Max: 1477600000Min: 2874700000 / Avg: 2876300000 / Max: 2878900000Min: 2735800000 / Avg: 2738200000 / Max: 2739600000Min: 5222900000 / Avg: 5229633333.33 / Max: 5235200000Min: 3040000000 / Avg: 3040900000 / Max: 3042300000Min: 5896900000 / Avg: 5904500000 / Max: 5910800000Min: 1574400000 / Avg: 1579300000 / Max: 1581900000Min: 3086200000 / Avg: 3086533333.33 / Max: 30871000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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: leblancbigEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620SE +/- 0.052359, N = 3SE +/- 0.012098, N = 5SE +/- 0.018519, N = 4SE +/- 0.024979, N = 6SE +/- 0.066662, N = 5SE +/- 0.069604, N = 12SE +/- 0.046356, N = 15SE +/- 0.035548, N = 15SE +/- 0.018568, N = 4SE +/- 0.011962, N = 718.0226308.36127613.1739206.0939586.6545413.6226825.9510633.31212511.3289904.7076101. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380510152025Min: 17.97 / Avg: 18.02 / Max: 18.13Min: 8.34 / Avg: 8.36 / Max: 8.39Min: 13.14 / Avg: 13.17 / Max: 13.22Min: 6 / Avg: 6.09 / Max: 6.18Min: 6.48 / Avg: 6.65 / Max: 6.82Min: 3.26 / Avg: 3.62 / Max: 4.09Min: 5.64 / Avg: 5.95 / Max: 6.38Min: 3.13 / Avg: 3.31 / Max: 3.56Min: 11.28 / Avg: 11.33 / Max: 11.37Min: 4.66 / Avg: 4.71 / Max: 4.741. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

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: BlowfishEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838040K80K120K160K200KSE +/- 4.00, N = 3SE +/- 7.09, N = 3SE +/- 585.27, N = 3SE +/- 11.00, N = 3SE +/- 4765.34, N = 12SE +/- 222.80, N = 3SE +/- 770.81, N = 3SE +/- 132.64, N = 3SE +/- 139.20, N = 33471968976493059744896938184506109274187380605531188691. (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: BlowfishEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030K60K90K120K150KMin: 34711 / Avg: 34719 / Max: 34723Min: 68962 / Avg: 68976 / Max: 68985Min: 96278 / Avg: 97448 / Max: 98064Min: 96927 / Avg: 96938 / Max: 96960Min: 132435 / Avg: 184506.17 / Max: 190848Min: 108866 / Avg: 109274.33 / Max: 109633Min: 185870 / Avg: 187380 / Max: 188404Min: 60288 / Avg: 60553 / Max: 60696Min: 118616 / Avg: 118869.33 / Max: 1190961. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

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 TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801122334455SE +/- 0.0899, N = 3SE +/- 0.0865, N = 3SE +/- 0.0170, N = 3SE +/- 0.0578, N = 3SE +/- 0.0225, N = 3SE +/- 0.1251, N = 15SE +/- 0.0805, N = 4SE +/- 0.1329, N = 15SE +/- 0.0744, N = 3SE +/- 0.0495, N = 448.392624.393834.323217.904217.95499.921916.12299.019426.873613.68251. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801020304050Min: 48.22 / Avg: 48.39 / Max: 48.51Min: 24.22 / Avg: 24.39 / Max: 24.51Min: 34.29 / Avg: 34.32 / Max: 34.35Min: 17.8 / Avg: 17.9 / Max: 17.99Min: 17.91 / Avg: 17.95 / Max: 17.98Min: 9.2 / Avg: 9.92 / Max: 10.7Min: 15.98 / Avg: 16.12 / Max: 16.35Min: 8.16 / Avg: 9.02 / Max: 9.75Min: 26.73 / Avg: 26.87 / Max: 26.96Min: 13.62 / Avg: 13.68 / Max: 13.831. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

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: sedovbigEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380612182430SE +/- 0.025165, N = 3SE +/- 0.030569, N = 4SE +/- 0.070436, N = 3SE +/- 0.023114, N = 4SE +/- 0.052822, N = 4SE +/- 0.027185, N = 5SE +/- 0.112742, N = 4SE +/- 0.047689, N = 5SE +/- 0.015026, N = 3SE +/- 0.010712, N = 427.36499014.02215020.28526010.39540011.1990205.6745159.9400625.17254223.84300014.4137901. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380612182430Min: 27.32 / Avg: 27.36 / Max: 27.4Min: 13.94 / Avg: 14.02 / Max: 14.09Min: 20.17 / Avg: 20.29 / Max: 20.41Min: 10.35 / Avg: 10.4 / Max: 10.46Min: 11.11 / Avg: 11.2 / Max: 11.34Min: 5.57 / Avg: 5.67 / Max: 5.73Min: 9.79 / Avg: 9.94 / Max: 10.27Min: 5.06 / Avg: 5.17 / Max: 5.31Min: 23.82 / Avg: 23.84 / Max: 23.87Min: 14.4 / Avg: 14.41 / Max: 14.441. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

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: CrownEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 4SE +/- 0.66, N = 4SE +/- 0.09, N = 6SE +/- 0.04, N = 5SE +/- 0.22, N = 6SE +/- 0.07, N = 3SE +/- 0.10, N = 521.2737.3429.2852.1353.2489.8862.78110.7436.0764.77MIN: 21 / MAX: 21.7MIN: 36.83 / MAX: 38.21MIN: 28.81 / MAX: 30MIN: 51.1 / MAX: 54.11MIN: 50.4 / MAX: 58.05MIN: 83.61 / MAX: 104.48MIN: 61.66 / MAX: 64.92MIN: 99.7 / MAX: 123.85MIN: 34.8 / MAX: 40.77MIN: 59.87 / MAX: 79.46
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 21.2 / Avg: 21.27 / Max: 21.36Min: 37.26 / Avg: 37.34 / Max: 37.39Min: 29.15 / Avg: 29.28 / Max: 29.42Min: 52.07 / Avg: 52.13 / Max: 52.17Min: 51.31 / Avg: 53.24 / Max: 54.3Min: 89.65 / Avg: 89.88 / Max: 90.18Min: 62.68 / Avg: 62.78 / Max: 62.9Min: 110.11 / Avg: 110.74 / Max: 111.64Min: 35.94 / Avg: 36.07 / Max: 36.16Min: 64.55 / Avg: 64.77 / Max: 65.05

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-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070140210280350SE +/- 0.07, N = 3SE +/- 0.73, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3333.72184.98239.52134.61133.1976.65111.9264.18195.16103.87
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300Min: 333.63 / Avg: 333.72 / Max: 333.85Min: 183.61 / Avg: 184.98 / Max: 186.1Min: 238.94 / Avg: 239.52 / Max: 239.84Min: 134.32 / Avg: 134.61 / Max: 134.79Min: 133.02 / Avg: 133.19 / Max: 133.37Min: 76.44 / Avg: 76.65 / Max: 76.78Min: 111.87 / Avg: 111.92 / Max: 112.02Min: 63.82 / Avg: 64.18 / Max: 64.39Min: 195.03 / Avg: 195.16 / Max: 195.34Min: 103.78 / Avg: 103.87 / Max: 103.95

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: CrownEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 4SE +/- 0.33, N = 4SE +/- 0.08, N = 6SE +/- 0.08, N = 5SE +/- 0.10, N = 6SE +/- 0.09, N = 4SE +/- 0.26, N = 519.3934.4226.7447.9648.0682.8357.58100.4344.1775.50MIN: 19.06 / MAX: 19.92MIN: 33.94 / MAX: 35.25MIN: 26.31 / MAX: 27.48MIN: 46.88 / MAX: 50.2MIN: 46.5 / MAX: 53.05MIN: 77.88 / MAX: 97.39MIN: 56.44 / MAX: 59.78MIN: 92.64 / MAX: 112.42MIN: 42.27 / MAX: 48.76MIN: 65.3 / MAX: 94.46
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 19.26 / Avg: 19.39 / Max: 19.52Min: 34.37 / Avg: 34.42 / Max: 34.47Min: 26.63 / Avg: 26.74 / Max: 26.9Min: 47.84 / Avg: 47.96 / Max: 48.06Min: 47.49 / Avg: 48.06 / Max: 48.94Min: 82.55 / Avg: 82.83 / Max: 83.12Min: 57.27 / Avg: 57.58 / Max: 57.71Min: 100.14 / Avg: 100.43 / Max: 100.87Min: 43.93 / Avg: 44.17 / Max: 44.34Min: 74.67 / Avg: 75.5 / Max: 76.03

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 AtomsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.26080.52160.78241.04321.304SE +/- 0.00016, N = 3SE +/- 0.00054, N = 3SE +/- 0.00070, N = 3SE +/- 0.00018, N = 3SE +/- 0.00050, N = 3SE +/- 0.00128, N = 3SE +/- 0.00036, N = 3SE +/- 0.00161, N = 4SE +/- 0.00101, N = 3SE +/- 0.00027, N = 31.159010.593420.837270.438670.451830.264630.383270.225460.518890.27064
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 1.16 / Avg: 1.16 / Max: 1.16Min: 0.59 / Avg: 0.59 / Max: 0.59Min: 0.84 / Avg: 0.84 / Max: 0.84Min: 0.44 / Avg: 0.44 / Max: 0.44Min: 0.45 / Avg: 0.45 / Max: 0.45Min: 0.26 / Avg: 0.26 / Max: 0.27Min: 0.38 / Avg: 0.38 / Max: 0.38Min: 0.22 / Avg: 0.23 / Max: 0.23Min: 0.52 / Avg: 0.52 / Max: 0.52Min: 0.27 / Avg: 0.27 / Max: 0.27

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 SceneEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380120240360480600SE +/- 0.07, N = 5SE +/- 0.13, N = 7SE +/- 0.15, N = 6SE +/- 0.34, N = 8SE +/- 0.20, N = 8SE +/- 2.11, N = 9SE +/- 0.26, N = 8SE +/- 0.74, N = 9SE +/- 0.17, N = 7SE +/- 0.57, N = 8108.15235.85156.11314.53272.45505.32293.34555.93184.56346.31
OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380100200300400500Min: 108.01 / Avg: 108.15 / Max: 108.37Min: 235.45 / Avg: 235.85 / Max: 236.36Min: 155.61 / Avg: 156.11 / Max: 156.54Min: 313.36 / Avg: 314.53 / Max: 315.93Min: 271.63 / Avg: 272.45 / Max: 273.31Min: 497.36 / Avg: 505.32 / Max: 514.85Min: 292 / Avg: 293.34 / Max: 294.41Min: 551.84 / Avg: 555.93 / Max: 558.59Min: 183.91 / Avg: 184.56 / Max: 185.18Min: 344.38 / Avg: 346.31 / Max: 348.5

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 GenerationEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215SE +/- 0.013, N = 4SE +/- 0.011, N = 7SE +/- 0.005, N = 5SE +/- 0.006, N = 8SE +/- 0.014, N = 7SE +/- 0.009, N = 10SE +/- 0.006, N = 8SE +/- 0.006, N = 10SE +/- 0.020, N = 6SE +/- 0.010, N = 912.3906.2638.8524.5334.9322.7144.4022.4227.1663.6931. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number GenerationEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620Min: 12.36 / Avg: 12.39 / Max: 12.41Min: 6.23 / Avg: 6.26 / Max: 6.31Min: 8.83 / Avg: 8.85 / Max: 8.87Min: 4.51 / Avg: 4.53 / Max: 4.55Min: 4.89 / Avg: 4.93 / Max: 5Min: 2.67 / Avg: 2.71 / Max: 2.77Min: 4.37 / Avg: 4.4 / Max: 4.43Min: 2.39 / Avg: 2.42 / Max: 2.46Min: 7.09 / Avg: 7.17 / Max: 7.22Min: 3.64 / Avg: 3.69 / Max: 3.731. (CXX) g++ options: -O3 -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 ISPC - Model: Asian DragonEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.13, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 4SE +/- 0.11, N = 4SE +/- 0.60, N = 15SE +/- 0.17, N = 5SE +/- 0.75, N = 5SE +/- 0.10, N = 5SE +/- 0.34, N = 621.1935.6529.7245.5356.4866.8565.4368.7458.29107.90MIN: 20.94 / MAX: 21.64MIN: 35.05 / MAX: 36.68MIN: 29.31 / MAX: 30.36MIN: 44.69 / MAX: 47.43MIN: 55.2 / MAX: 59.21MIN: 59.64 / MAX: 72.74MIN: 63.59 / MAX: 67.61MIN: 62.77 / MAX: 75.12MIN: 53.64 / MAX: 61.72MIN: 96.18 / MAX: 112.26
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 21.02 / Avg: 21.19 / Max: 21.44Min: 35.28 / Avg: 35.65 / Max: 35.86Min: 29.5 / Avg: 29.72 / Max: 29.92Min: 45.29 / Avg: 45.53 / Max: 45.89Min: 56.29 / Avg: 56.48 / Max: 56.74Min: 63.07 / Avg: 66.85 / Max: 69.78Min: 64.81 / Avg: 65.43 / Max: 65.77Min: 66.41 / Avg: 68.74 / Max: 70.76Min: 57.97 / Avg: 58.29 / Max: 58.53Min: 106.42 / Avg: 107.9 / Max: 108.68

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: OpenMPEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805K10K15K20K25KSE +/- 2.42, N = 5SE +/- 3.28, N = 4SE +/- 7.80, N = 6SE +/- 3.07, N = 6SE +/- 39.22, N = 15SE +/- 1.33, N = 6SE +/- 31.72, N = 8SE +/- 13.75, N = 4SE +/- 8.35, N = 6212711097615258786382034866732243271405772811. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804K8K12K16K20KMin: 10968 / Avg: 10976.4 / Max: 10981Min: 15248 / Avg: 15257.5 / Max: 15263Min: 7830 / Avg: 7863.33 / Max: 7885Min: 8193 / Avg: 8203.17 / Max: 8212Min: 4607 / Avg: 4866.07 / Max: 5082Min: 7318 / Avg: 7321.67 / Max: 7326Min: 4234 / Avg: 4326.88 / Max: 4491Min: 14039 / Avg: 14057 / Max: 14098Min: 7250 / Avg: 7280.5 / Max: 73011. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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 19EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804080120160200SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.55, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.27, N = 3SE +/- 0.33, N = 3173.3991.12124.4766.6167.7039.4960.7435.38102.0354.92
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380306090120150Min: 173.35 / Avg: 173.39 / Max: 173.43Min: 91.03 / Avg: 91.12 / Max: 91.26Min: 124.45 / Avg: 124.47 / Max: 124.49Min: 66.5 / Avg: 66.61 / Max: 66.68Min: 67.61 / Avg: 67.7 / Max: 67.77Min: 38.75 / Avg: 39.49 / Max: 40.58Min: 60.66 / Avg: 60.74 / Max: 60.8Min: 35.29 / Avg: 35.38 / Max: 35.52Min: 101.52 / Avg: 102.03 / Max: 102.4Min: 54.43 / Avg: 54.92 / Max: 55.54

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 LavaMDEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380306090120150SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.66, N = 3SE +/- 0.24, N = 3114.4759.9582.5443.7348.0825.9341.5223.4671.9939.071. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 114.43 / Avg: 114.47 / Max: 114.51Min: 59.89 / Avg: 59.95 / Max: 60.04Min: 82.49 / Avg: 82.54 / Max: 82.59Min: 43.68 / Avg: 43.73 / Max: 43.78Min: 48.06 / Avg: 48.08 / Max: 48.1Min: 25.8 / Avg: 25.93 / Max: 26.02Min: 41.5 / Avg: 41.52 / Max: 41.52Min: 23.41 / Avg: 23.46 / Max: 23.5Min: 71.16 / Avg: 71.99 / Max: 73.29Min: 38.6 / Avg: 39.07 / Max: 39.351. (CXX) g++ options: -O2 -lOpenCL

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 - DegriddingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838010K20K30K40K50KSE +/- 68.60, N = 3SE +/- 137.23, N = 3SE +/- 183.26, N = 3SE +/- 229.07, N = 3SE +/- 66.60, N = 3SE +/- 128.17, N = 3SE +/- 220.84, N = 3SE +/- 316.80, N = 3SE +/- 37.57, N = 3SE +/- 73.04, N = 310427.2020854.5012839.8024994.3020446.8040240.4022987.8044826.509239.5918222.501. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808K16K24K32K40KMin: 10290 / Avg: 10427.2 / Max: 10495.8Min: 20580 / Avg: 20854.47 / Max: 20991.7Min: 12495 / Avg: 12839.83 / Max: 13119.8Min: 24599.6 / Avg: 24994.27 / Max: 25393.1Min: 20380.2 / Avg: 20446.8 / Max: 20580Min: 39984.1 / Avg: 40240.43 / Max: 40368.6Min: 22571.7 / Avg: 22987.83 / Max: 23324.1Min: 44192.9 / Avg: 44826.5 / Max: 45143.3Min: 9174.67 / Avg: 9239.59 / Max: 9304.81Min: 18096.3 / Avg: 18222.5 / Max: 18349.31. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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.3840x2160EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.67281.34562.01842.69123.364SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 50.621.140.841.541.432.251.662.551.792.99
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 0.61 / Avg: 0.62 / Max: 0.62Min: 1.14 / Avg: 1.14 / Max: 1.14Min: 0.84 / Avg: 0.84 / Max: 0.84Min: 1.54 / Avg: 1.54 / Max: 1.55Min: 1.43 / Avg: 1.43 / Max: 1.43Min: 2.24 / Avg: 2.25 / Max: 2.26Min: 1.66 / Avg: 1.66 / Max: 1.66Min: 2.55 / Avg: 2.55 / Max: 2.56Min: 1.79 / Avg: 1.79 / Max: 1.79Min: 2.97 / Avg: 2.99 / Max: 3

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.67051.3412.01152.6823.3525SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 50.621.140.841.541.422.241.662.521.782.98
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 0.62 / Avg: 0.62 / Max: 0.62Min: 1.13 / Avg: 1.14 / Max: 1.14Min: 0.84 / Avg: 0.84 / Max: 0.84Min: 1.53 / Avg: 1.54 / Max: 1.54Min: 1.42 / Avg: 1.42 / Max: 1.43Min: 2.22 / Avg: 2.24 / Max: 2.25Min: 1.66 / Avg: 1.66 / Max: 1.66Min: 2.5 / Avg: 2.52 / Max: 2.54Min: 1.77 / Avg: 1.78 / Max: 1.78Min: 2.98 / Avg: 2.98 / Max: 2.99

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-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.32, N = 3SE +/- 0.04, N = 3SE +/- 0.22, N = 3SE +/- 0.01, N = 3SE +/- 0.20, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3275.29140.29195.24102.12105.6567.1393.9957.71164.0187.63
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050100150200250Min: 274.93 / Avg: 275.29 / Max: 275.95Min: 140.09 / Avg: 140.29 / Max: 140.4Min: 195.07 / Avg: 195.24 / Max: 195.52Min: 101.49 / Avg: 102.12 / Max: 102.54Min: 105.6 / Avg: 105.65 / Max: 105.73Min: 66.84 / Avg: 67.13 / Max: 67.55Min: 93.96 / Avg: 93.99 / Max: 94.01Min: 57.31 / Avg: 57.71 / Max: 57.95Min: 163.88 / Avg: 164.01 / Max: 164.24Min: 87.6 / Avg: 87.63 / Max: 87.66

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.4096x4096EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.3240.6480.9721.2961.62SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.310.570.420.770.701.090.821.250.851.44
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 0.31 / Avg: 0.31 / Max: 0.31Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.42 / Avg: 0.42 / Max: 0.42Min: 0.77 / Avg: 0.77 / Max: 0.77Min: 0.7 / Avg: 0.7 / Max: 0.7Min: 1.08 / Avg: 1.09 / Max: 1.11Min: 0.81 / Avg: 0.82 / Max: 0.82Min: 1.24 / Avg: 1.25 / Max: 1.26Min: 0.85 / Avg: 0.85 / Max: 0.85Min: 1.43 / Avg: 1.44 / Max: 1.44

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: f32 - Engine: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.59111.18221.77332.36442.9555SE +/- 0.003678, N = 7SE +/- 0.001570, N = 7SE +/- 0.003974, N = 7SE +/- 0.002088, N = 7SE +/- 0.000729, N = 7SE +/- 0.002491, N = 7SE +/- 0.000830, N = 7SE +/- 0.002533, N = 7SE +/- 0.000410, N = 7SE +/- 0.003046, N = 72.6273101.2035602.0344700.9009220.9453810.6310000.8498630.5789521.4595201.397170MIN: 2.46MIN: 0.96MIN: 1.85MIN: 0.77MIN: 0.85MIN: 0.56MIN: 0.8MIN: 0.52MIN: 1.43MIN: 1.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 2.61 / Avg: 2.63 / Max: 2.64Min: 1.2 / Avg: 1.2 / Max: 1.21Min: 2.03 / Avg: 2.03 / Max: 2.05Min: 0.9 / Avg: 0.9 / Max: 0.91Min: 0.94 / Avg: 0.95 / Max: 0.95Min: 0.62 / Avg: 0.63 / Max: 0.64Min: 0.85 / Avg: 0.85 / Max: 0.85Min: 0.57 / Avg: 0.58 / Max: 0.59Min: 1.46 / Avg: 1.46 / Max: 1.46Min: 1.39 / Avg: 1.4 / Max: 1.411. (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.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838010K20K30K40K50KSE +/- 277.67, N = 3SE +/- 378.67, N = 3SE +/- 233.31, N = 3SE +/- 0.00, N = 3SE +/- 75.13, N = 3SE +/- 144.23, N = 3SE +/- 184.93, N = 3SE +/- 626.39, N = 3SE +/- 49.28, N = 3SE +/- 93.94, N = 312217.024232.814495.728113.821791.242695.924224.047724.710580.920662.01. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808K16K24K32K40KMin: 11662 / Avg: 12217.33 / Max: 12495Min: 23854.1 / Avg: 24232.77 / Max: 24990.1Min: 14056.9 / Avg: 14495.67 / Max: 14852.6Min: 28113.8 / Avg: 28113.8 / Max: 28113.8Min: 21640.9 / Avg: 21791.17 / Max: 21866.3Min: 42407.4 / Avg: 42695.87 / Max: 42840.1Min: 23854.1 / Avg: 24223.97 / Max: 24408.9Min: 46648.1 / Avg: 47724.73 / Max: 48817.8Min: 10495.8 / Avg: 10580.93 / Max: 10666.5Min: 20499.7 / Avg: 20661.97 / Max: 20825.11. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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: 1MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838012K24K36K48K60KSE +/- 46.88, N = 3SE +/- 55.72, N = 3SE +/- 59.29, N = 3SE +/- 117.18, N = 3SE +/- 53.23, N = 3SE +/- 108.00, N = 3SE +/- 54.06, N = 3SE +/- 145.93, N = 3SE +/- 6.99, N = 3SE +/- 67.30, N = 312650.020697.817437.628086.228145.250909.231822.056659.114658.226504.21. (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: 1MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838010K20K30K40K50KMin: 12559.8 / Avg: 12649.97 / Max: 12717.3Min: 20615.2 / Avg: 20697.83 / Max: 20803.9Min: 17331 / Avg: 17437.6 / Max: 17535.9Min: 27894.8 / Avg: 28086.17 / Max: 28299Min: 28043.4 / Avg: 28145.17 / Max: 28223.1Min: 50761.4 / Avg: 50909.17 / Max: 51119.5Min: 31743 / Avg: 31821.97 / Max: 31925.4Min: 56417.5 / Avg: 56659.07 / Max: 56921.7Min: 14644.3 / Avg: 14658.17 / Max: 14666.6Min: 26372 / Avg: 26504.2 / Max: 26592.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

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 SecondEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380700K1400K2100K2800K3500KSE +/- 205.09, N = 3SE +/- 4027.99, N = 3SE +/- 3121.59, N = 3SE +/- 17046.92, N = 3SE +/- 7766.73, N = 3SE +/- 24427.40, N = 3SE +/- 2078.06, N = 3SE +/- 21695.70, N = 3SE +/- 1975.05, N = 3SE +/- 1412.48, N = 3731356.711442185.721046268.851998209.201982329.093001332.222113523.173220418.061206142.702365407.621. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380600K1200K1800K2400K3000KMin: 731003.89 / Avg: 731356.71 / Max: 731714.29Min: 1435755.55 / Avg: 1442185.72 / Max: 1449603.62Min: 1041497.15 / Avg: 1046268.85 / Max: 1052141.27Min: 1969937.93 / Avg: 1998209.2 / Max: 2028847.68Min: 1966810.08 / Avg: 1982329.09 / Max: 1990668.74Min: 2975533.21 / Avg: 3001332.22 / Max: 3050160.85Min: 2110904.97 / Avg: 2113523.17 / Max: 2117627.6Min: 3183089.84 / Avg: 3220418.06 / Max: 3258241.06Min: 1202194 / Avg: 1206142.7 / Max: 1208208.26Min: 2363542.36 / Avg: 2365407.62 / Max: 2368177.611. (CC) gcc options: -O2 -lrt" -lrt

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: SharpenEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802004006008001000SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 4.48, N = 3SE +/- 1.45, N = 32023632814854947835838823706721. (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: SharpenEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380150300450600750Min: 362 / Avg: 363.33 / Max: 364Min: 482 / Avg: 485.33 / Max: 487Min: 873 / Avg: 881.67 / Max: 888Min: 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

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_bareEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215SE +/- 0.002, N = 3SE +/- 0.006, N = 3SE +/- 0.005, N = 3SE +/- 0.015, N = 3SE +/- 0.008, N = 3SE +/- 0.057, N = 3SE +/- 0.004, N = 3SE +/- 0.055, N = 3SE +/- 0.010, N = 3SE +/- 0.005, N = 32.3864.0563.1495.1905.1208.5185.68410.1765.0179.0631. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215Min: 2.38 / Avg: 2.39 / Max: 2.39Min: 4.04 / Avg: 4.06 / Max: 4.06Min: 3.14 / Avg: 3.15 / Max: 3.16Min: 5.17 / Avg: 5.19 / Max: 5.22Min: 5.11 / Avg: 5.12 / Max: 5.13Min: 8.41 / Avg: 8.52 / Max: 8.59Min: 5.68 / Avg: 5.68 / Max: 5.69Min: 10.07 / Avg: 10.18 / Max: 10.26Min: 5 / Avg: 5.02 / Max: 5.04Min: 9.05 / Avg: 9.06 / Max: 9.071. (CXX) g++ options: -O3 -pthread

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 4SE +/- 0.01, N = 3SE +/- 0.18, N = 15SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 33.265.664.587.878.3112.239.5313.555.509.41MIN: 3.15 / MAX: 3.42MIN: 5.46 / MAX: 6.24MIN: 4.44 / MAX: 4.84MIN: 7.52 / MAX: 8.87MIN: 8.16 / MAX: 9.08MIN: 11 / MAX: 15.76MIN: 9.22 / MAX: 10.3MIN: 12.53 / MAX: 18.71MIN: 5.29 / MAX: 6.23MIN: 8.72 / MAX: 12.17
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620Min: 3.23 / Avg: 3.26 / Max: 3.29Min: 5.64 / Avg: 5.66 / Max: 5.68Min: 4.55 / Avg: 4.58 / Max: 4.61Min: 7.73 / Avg: 7.87 / Max: 8.15Min: 8.3 / Avg: 8.31 / Max: 8.32Min: 11.58 / Avg: 12.23 / Max: 13.83Min: 9.4 / Avg: 9.53 / Max: 9.74Min: 13.34 / Avg: 13.55 / Max: 13.72Min: 5.49 / Avg: 5.5 / Max: 5.5Min: 9.27 / Avg: 9.41 / Max: 9.56

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 35.038.676.9811.7511.8018.1613.2620.748.9514.33MIN: 4.71 / MAX: 5.13MIN: 7.5 / MAX: 9.29MIN: 6.23 / MAX: 7.31MIN: 10.22 / MAX: 13.36MIN: 10.29 / MAX: 13.32MIN: 15.6 / MAX: 24.41MIN: 11.63 / MAX: 15.65MIN: 18.12 / MAX: 28.76MIN: 7.51 / MAX: 10.05MIN: 11.53 / MAX: 18.29
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380510152025Min: 5.02 / Avg: 5.03 / Max: 5.04Min: 8.61 / Avg: 8.67 / Max: 8.72Min: 6.97 / Avg: 6.98 / Max: 6.98Min: 11.59 / Avg: 11.75 / Max: 11.89Min: 11.57 / Avg: 11.8 / Max: 12Min: 18.02 / Avg: 18.16 / Max: 18.28Min: 13.14 / Avg: 13.26 / Max: 13.48Min: 20.57 / Avg: 20.74 / Max: 20.83Min: 8.88 / Avg: 8.95 / Max: 9.02Min: 14.07 / Avg: 14.33 / Max: 14.53

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-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 387.3646.0162.5234.6535.5323.7031.9721.3051.0528.24
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 87.23 / Avg: 87.36 / Max: 87.52Min: 45.88 / Avg: 46.01 / Max: 46.12Min: 62.34 / Avg: 62.52 / Max: 62.62Min: 34.57 / Avg: 34.65 / Max: 34.71Min: 35.37 / Avg: 35.53 / Max: 35.72Min: 23.51 / Avg: 23.7 / Max: 23.85Min: 31.87 / Avg: 31.97 / Max: 32.13Min: 21.25 / Avg: 21.3 / Max: 21.38Min: 50.89 / Avg: 51.05 / Max: 51.21Min: 27.86 / Avg: 28.24 / Max: 28.65

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 WritingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803M6M9M12M15MSE +/- 33136.81, N = 3SE +/- 39674.91, N = 3SE +/- 53444.98, N = 3SE +/- 52297.79, N = 3SE +/- 59078.01, N = 15SE +/- 193578.05, N = 14SE +/- 25051.94, N = 3SE +/- 217578.12, N = 15SE +/- 63537.44, N = 3SE +/- 103809.83, N = 153656213568837950814227420817877820214966330928868914789793667655691702601. (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 WritingEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803M6M9M12M15MMin: 3591972 / Avg: 3656213 / Max: 3702439Min: 5630486 / Avg: 5688378.67 / Max: 5764321Min: 5024815 / Avg: 5081421.67 / Max: 5188248Min: 7328953 / Avg: 7420817 / Max: 7510061Min: 8041472 / Avg: 8778202.2 / Max: 9053959Min: 13860819 / Avg: 14966330.07 / Max: 16322822Min: 9242482 / Avg: 9288689 / Max: 9328570Min: 13677213 / Avg: 14789793 / Max: 16889778Min: 6612056 / Avg: 6676556 / Max: 6803626Min: 8582562 / Avg: 9170259.73 / Max: 99885331. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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 digitEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070140210280350SE +/- 0.19, N = 3SE +/- 0.22, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.79, N = 3SE +/- 0.07, N = 3SE +/- 10.61, N = 12SE +/- 0.57, N = 3SE +/- 0.89, N = 3326.75162.85233.04119.51128.07145.56115.85108.82161.6581.461. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300Min: 326.5 / Avg: 326.75 / Max: 327.12Min: 162.42 / Avg: 162.85 / Max: 163.16Min: 232.98 / Avg: 233.04 / Max: 233.13Min: 119.37 / Avg: 119.51 / Max: 119.7Min: 127.74 / Avg: 128.07 / Max: 128.32Min: 144.29 / Avg: 145.56 / Max: 147.02Min: 115.78 / Avg: 115.85 / Max: 116Min: 63.09 / Avg: 108.82 / Max: 146.07Min: 160.64 / Avg: 161.65 / Max: 162.61Min: 79.97 / Avg: 81.46 / Max: 83.051. (CC) gcc options: -O2 -pthread

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 TestEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380110K220K330K440K550KSE +/- 114.29, N = 3SE +/- 1070.23, N = 3SE +/- 601.60, N = 3SE +/- 2227.12, N = 3SE +/- 405.04, N = 3SE +/- 3325.25, N = 3SE +/- 1233.93, N = 3SE +/- 2304.69, N = 3SE +/- 596.42, N = 3SE +/- 3489.62, N = 31236732070341709722864803006904524673347294958782015963551401. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838090K180K270K360K450KMin: 123529 / Avg: 123673.33 / Max: 123899Min: 204911 / Avg: 207034.33 / Max: 208330Min: 169928 / Avg: 170972 / Max: 172012Min: 282462 / Avg: 286479.67 / Max: 290154Min: 300005 / Avg: 300690 / Max: 301407Min: 445869 / Avg: 452466.67 / Max: 456490Min: 333158 / Avg: 334729.33 / Max: 337163Min: 491394 / Avg: 495878.33 / Max: 499044Min: 200567 / Avg: 201596 / Max: 202633Min: 348805 / Avg: 355139.67 / Max: 3608441. (CXX) g++ options: -pipe -lpthread

LULESH

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

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808K16K24K32K40KSE +/- 26.64, N = 7SE +/- 151.69, N = 5SE +/- 26.78, N = 7SE +/- 63.67, N = 5SE +/- 337.89, N = 12SE +/- 247.65, N = 3SE +/- 24.80, N = 3SE +/- 282.51, N = 3SE +/- 16.09, N = 5SE +/- 62.90, N = 49345.6623367.919333.1623653.5318128.9435233.2518991.1336956.2118779.6535311.851. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83806K12K18K24K30KMin: 9225.21 / Avg: 9345.66 / Max: 9433.51Min: 23007.22 / Avg: 23367.91 / Max: 23889.58Min: 9252.55 / Avg: 9333.16 / Max: 9432.49Min: 23524.66 / Avg: 23653.53 / Max: 23849.35Min: 14421.16 / Avg: 18128.94 / Max: 18602.59Min: 34749.15 / Avg: 35233.25 / Max: 35565.98Min: 18955.08 / Avg: 18991.13 / Max: 19038.67Min: 36431.85 / Avg: 36956.21 / Max: 37400.67Min: 18728.75 / Avg: 18779.64 / Max: 18815.44Min: 35149.62 / Avg: 35311.85 / Max: 35445.041. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi

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: EnhancedEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030060090012001500SE +/- 0.58, N = 3SE +/- 1.00, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 5.61, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 337563851583888013361052144964111251. (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: EnhancedEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030060090012001500Min: 374 / Avg: 375 / Max: 376Min: 514 / Avg: 515 / Max: 517Min: 1335 / Avg: 1336.33 / Max: 1338Min: 1051 / Avg: 1051.67 / Max: 1052Min: 1438 / Avg: 1448.67 / Max: 1457Min: 640 / Avg: 641.33 / Max: 643Min: 1124 / Avg: 1125.33 / Max: 11261. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -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: BT.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060K120K180K240K300KSE +/- 53.02, N = 3SE +/- 158.61, N = 3SE +/- 29.08, N = 3SE +/- 166.51, N = 3SE +/- 54.19, N = 3SE +/- 144.12, N = 4SE +/- 105.34, N = 3SE +/- 631.22, N = 4SE +/- 204.16, N = 3SE +/- 236.31, N = 467984.34109453.7570079.25138196.30129163.40237936.82136092.40256826.35117333.47198052.381. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838040K80K120K160K200KMin: 67880.61 / Avg: 67984.34 / Max: 68055.27Min: 109150.05 / Avg: 109453.75 / Max: 109684.93Min: 70025.87 / Avg: 70079.25 / Max: 70125.95Min: 137887.36 / Avg: 138196.3 / Max: 138458.43Min: 129061.85 / Avg: 129163.4 / Max: 129246.97Min: 237721.46 / Avg: 237936.82 / Max: 238361.47Min: 135946.72 / Avg: 136092.4 / Max: 136297.04Min: 255920.13 / Avg: 256826.35 / Max: 258668.11Min: 117004.88 / Avg: 117333.47 / Max: 117707.68Min: 197468.65 / Avg: 198052.38 / Max: 198558.71. (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

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 1080pEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801326395265SE +/- 0.08, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.24, N = 3SE +/- 0.33, N = 6SE +/- 0.39, N = 15SE +/- 0.23, N = 4SE +/- 0.62, N = 5SE +/- 0.06, N = 3SE +/- 0.32, N = 314.9428.3720.7937.2834.6449.8140.1356.2823.7037.491. (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 1080pEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801122334455Min: 14.78 / Avg: 14.94 / Max: 15.03Min: 27.84 / Avg: 28.37 / Max: 28.74Min: 20.56 / Avg: 20.79 / Max: 20.91Min: 36.81 / Avg: 37.28 / Max: 37.56Min: 33 / Avg: 34.64 / Max: 35.05Min: 45.39 / Avg: 49.81 / Max: 51.84Min: 39.45 / Avg: 40.13 / Max: 40.52Min: 53.87 / Avg: 56.28 / Max: 57.3Min: 23.63 / Avg: 23.7 / Max: 23.82Min: 37.07 / Avg: 37.49 / Max: 38.121. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060K120K180K240K300KSE +/- 65.93, N = 3SE +/- 885.97, N = 4SE +/- 741.02, N = 3SE +/- 726.58, N = 4SE +/- 514.37, N = 3SE +/- 2211.94, N = 4SE +/- 1144.30, N = 4SE +/- 1551.26, N = 5SE +/- 47.08, N = 3SE +/- 58.73, N = 476603.34139874.5776463.09141063.75136132.33261304.67143783.01287566.1098453.55188790.141. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050K100K150K200K250KMin: 76509.93 / Avg: 76603.34 / Max: 76730.64Min: 137335.22 / Avg: 139874.57 / Max: 141458.55Min: 75012.93 / Avg: 76463.09 / Max: 77452.93Min: 139214.96 / Avg: 141063.75 / Max: 142756.4Min: 135173.08 / Avg: 136132.33 / Max: 136933.86Min: 256591.78 / Avg: 261304.67 / Max: 266022.55Min: 140499.12 / Avg: 143783.01 / Max: 145744.94Min: 282427.56 / Avg: 287566.1 / Max: 290702.08Min: 98396.26 / Avg: 98453.55 / Max: 98546.9Min: 188681.84 / Avg: 188790.14 / Max: 188925.831. (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

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-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380306090120150SE +/- 0.03, N = 3SE +/- 0.27, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3113.0462.3781.2648.5950.5734.4946.0130.7174.5144.45
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100Min: 113.01 / Avg: 113.04 / Max: 113.1Min: 62.01 / Avg: 62.37 / Max: 62.89Min: 81.19 / Avg: 81.26 / Max: 81.3Min: 48.4 / Avg: 48.59 / Max: 48.75Min: 50.51 / Avg: 50.57 / Max: 50.61Min: 34.17 / Avg: 34.49 / Max: 34.74Min: 45.94 / Avg: 46.01 / Max: 46.06Min: 30.61 / Avg: 30.71 / Max: 30.81Min: 74.24 / Avg: 74.51 / Max: 74.76Min: 44.25 / Avg: 44.45 / Max: 44.6

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: u8s8f32 - Engine: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83800.69941.39882.09822.79763.497SE +/- 0.017223, N = 7SE +/- 0.026073, N = 15SE +/- 0.006542, N = 7SE +/- 0.021823, N = 15SE +/- 0.003555, N = 7SE +/- 0.042741, N = 15SE +/- 0.002569, N = 7SE +/- 0.033927, N = 15SE +/- 0.000981, N = 7SE +/- 0.002416, N = 73.1084502.6817702.8468402.7017601.6381901.0153461.6062700.8540501.4825600.915086MIN: 2.78MIN: 2.03MIN: 2.73MIN: 2.21MIN: 1.55MIN: 0.46MIN: 1.54MIN: 0.42MIN: 1.32MIN: 0.851. (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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 3.05 / Avg: 3.11 / Max: 3.2Min: 2.53 / Avg: 2.68 / Max: 2.94Min: 2.83 / Avg: 2.85 / Max: 2.88Min: 2.58 / Avg: 2.7 / Max: 2.92Min: 1.63 / Avg: 1.64 / Max: 1.65Min: 0.78 / Avg: 1.02 / Max: 1.44Min: 1.6 / Avg: 1.61 / Max: 1.62Min: 0.64 / Avg: 0.85 / Max: 1.07Min: 1.48 / Avg: 1.48 / Max: 1.49Min: 0.91 / Avg: 0.92 / Max: 0.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 1MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838010K20K30K40K50KSE +/- 11.70, N = 3SE +/- 41.86, N = 3SE +/- 41.58, N = 3SE +/- 49.70, N = 3SE +/- 171.67, N = 3SE +/- 37.01, N = 3SE +/- 57.86, N = 3SE +/- 108.22, N = 3SE +/- 73.93, N = 3SE +/- 97.10, N = 313477.821774.819754.731611.137011.241905.442371.847971.323539.942770.81. (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: 1MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808K16K24K32K40KMin: 13455 / Avg: 13477.77 / Max: 13493.8Min: 21694.3 / Avg: 21774.77 / Max: 21835Min: 19705.2 / Avg: 19754.67 / Max: 19837.3Min: 31521.9 / Avg: 31611.07 / Max: 31693.7Min: 36808 / Avg: 37011.23 / Max: 37352.5Min: 41841 / Avg: 41905.37 / Max: 41969.2Min: 42256.5 / Avg: 42371.83 / Max: 42437.6Min: 47769.2 / Avg: 47971.33 / Max: 48139.4Min: 23393.5 / Avg: 23539.87 / Max: 23631.2Min: 42578.6 / Avg: 42770.83 / Max: 42890.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 7713EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838014K28K42K56K70KSE +/- 149.52, N = 9SE +/- 351.69, N = 15SE +/- 184.94, N = 15SE +/- 664.12, N = 3SE +/- 466.02, N = 3SE +/- 621.72, N = 15SE +/- 131.93, N = 3SE +/- 308.74, N = 31874534134258434651543664563023534766328
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 7713EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838011K22K33K44K55KMin: 17678 / Avg: 18745.44 / Max: 19182Min: 31557 / Avg: 34133.87 / Max: 35848Min: 24776 / Avg: 25842.87 / Max: 26948Min: 45189 / Avg: 46514.67 / Max: 47249Min: 42807 / Avg: 43663.67 / Max: 44410Min: 52386 / Avg: 56302.27 / Max: 58925Min: 35091 / Avg: 35346.67 / Max: 35531Min: 65816 / Avg: 66328.33 / Max: 66883

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 DragonEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.16, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 4SE +/- 0.14, N = 5SE +/- 0.50, N = 15SE +/- 0.16, N = 5SE +/- 0.70, N = 5SE +/- 0.50, N = 4SE +/- 0.22, N = 523.6338.1733.0648.2962.8970.1069.4271.0042.6183.57MIN: 23.29 / MAX: 24.17MIN: 37.52 / MAX: 39.57MIN: 32.75 / MAX: 33.62MIN: 47.51 / MAX: 49.84MIN: 61.26 / MAX: 65.99MIN: 64.7 / MAX: 75.8MIN: 67.34 / MAX: 71.37MIN: 64.9 / MAX: 76.73MIN: 39.84 / MAX: 49.36MIN: 69.17 / MAX: 92.21
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801632486480Min: 23.43 / Avg: 23.63 / Max: 23.93Min: 37.77 / Avg: 38.17 / Max: 38.68Min: 32.94 / Avg: 33.06 / Max: 33.22Min: 48.17 / Avg: 48.29 / Max: 48.48Min: 62.36 / Avg: 62.89 / Max: 63.11Min: 67.36 / Avg: 70.1 / Max: 73.17Min: 68.83 / Avg: 69.42 / Max: 69.82Min: 68.65 / Avg: 71 / Max: 72.85Min: 41.71 / Avg: 42.61 / Max: 43.71Min: 83.06 / Avg: 83.57 / Max: 84.37

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 V2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380300K600K900K1200K1500KSE +/- 217.79, N = 3SE +/- 3519.89, N = 3SE +/- 1094.00, N = 3SE +/- 6529.50, N = 8SE +/- 1048.23, N = 3SE +/- 8114.15, N = 15SE +/- 2826.71, N = 3SE +/- 4424.64, N = 15SE +/- 276.22, N = 3SE +/- 1484.41, N = 3138571086697411165137815556127584509945848743949531026060572750
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380200K400K600K800K1000KMin: 1385400 / Avg: 1385710 / Max: 1386130Min: 860928 / Avg: 866973.67 / Max: 873120Min: 1114900 / Avg: 1116513.33 / Max: 1118600Min: 757328 / Avg: 781555.38 / Max: 804737Min: 611689 / Avg: 612757.67 / Max: 614854Min: 413265 / Avg: 450994.4 / Max: 514682Min: 579340 / Avg: 584874 / Max: 588642Min: 367999 / Avg: 394952.67 / Max: 435354Min: 1025660 / Avg: 1026060 / Max: 1026590Min: 571155 / Avg: 572750 / Max: 575716

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 TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380612182430SE +/- 0.051, N = 3SE +/- 0.006, N = 4SE +/- 0.034, N = 3SE +/- 0.042, N = 4SE +/- 0.028, N = 4SE +/- 0.036, N = 5SE +/- 0.020, N = 4SE +/- 0.034, N = 5SE +/- 0.041, N = 3SE +/- 0.039, N = 525.24813.89718.39010.40010.5827.7399.7307.29915.5159.2571. (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 TimeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380612182430Min: 25.16 / Avg: 25.25 / Max: 25.33Min: 13.89 / Avg: 13.9 / Max: 13.91Min: 18.33 / Avg: 18.39 / Max: 18.45Min: 10.32 / Avg: 10.4 / Max: 10.5Min: 10.52 / Avg: 10.58 / Max: 10.65Min: 7.63 / Avg: 7.74 / Max: 7.85Min: 9.67 / Avg: 9.73 / Max: 9.77Min: 7.19 / Avg: 7.3 / Max: 7.4Min: 15.46 / Avg: 15.52 / Max: 15.59Min: 9.13 / Avg: 9.26 / Max: 9.381. (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

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: NinjaEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070140210280350SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 3SE +/- 0.42, N = 3SE +/- 0.29, N = 3SE +/- 0.47, N = 3SE +/- 0.23, N = 3SE +/- 0.93, N = 3SE +/- 0.54, N = 3340.49188.61253.67149.50161.83106.52145.5798.72208.65127.99
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300Min: 340.4 / Avg: 340.49 / Max: 340.56Min: 188.34 / Avg: 188.61 / Max: 188.78Min: 253.5 / Avg: 253.67 / Max: 253.98Min: 149.21 / Avg: 149.5 / Max: 149.69Min: 160.99 / Avg: 161.83 / Max: 162.26Min: 106.11 / Avg: 106.52 / Max: 107.09Min: 145 / Avg: 145.57 / Max: 146.51Min: 98.31 / Avg: 98.72 / Max: 99.09Min: 207.08 / Avg: 208.65 / Max: 210.3Min: 127.2 / Avg: 127.99 / Max: 129.04

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 4SE +/- 0.09, N = 15SE +/- 0.02, N = 3SE +/- 0.11, N = 15SE +/- 0.02, N = 3SE +/- 0.07, N = 32.514.383.595.796.417.717.508.544.426.97MIN: 0.81 / MAX: 2.95MIN: 1.76 / MAX: 5.02MIN: 1.32 / MAX: 4.17MIN: 2.29 / MAX: 6.82MIN: 2.52 / MAX: 7.64MIN: 2.64 / MAX: 10.09MIN: 3.03 / MAX: 8.73MIN: 3.07 / MAX: 11.07MIN: 1.74 / MAX: 5.11MIN: 3.13 / MAX: 8.11
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215Min: 2.47 / Avg: 2.51 / Max: 2.53Min: 4.31 / Avg: 4.38 / Max: 4.45Min: 3.56 / Avg: 3.59 / Max: 3.61Min: 5.68 / Avg: 5.79 / Max: 5.85Min: 6.32 / Avg: 6.41 / Max: 6.61Min: 7.05 / Avg: 7.71 / Max: 8.29Min: 7.48 / Avg: 7.5 / Max: 7.54Min: 8.03 / Avg: 8.54 / Max: 9.18Min: 4.39 / Avg: 4.42 / Max: 4.44Min: 6.84 / Avg: 6.97 / Max: 7.07

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: vklBenchmarkEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802004006008001000SE +/- 0.67, N = 3SE +/- 2.85, N = 3SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 6.91, N = 9SE +/- 3.46, N = 3SE +/- 7.00, N = 3SE +/- 3.53, N = 3254400348489582571636611641820MIN: 1 / MAX: 963MIN: 1 / MAX: 1548MIN: 1 / MAX: 1316MIN: 1 / MAX: 1791MIN: 1 / MAX: 2142MIN: 1 / MAX: 1746MIN: 1 / MAX: 2351MIN: 1 / MAX: 1753MIN: 1 / MAX: 2858MIN: 1 / MAX: 3230
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380140280420560700Min: 253 / Avg: 253.67 / Max: 255Min: 394 / Avg: 399.67 / Max: 403Min: 345 / Avg: 347.67 / Max: 350Min: 488 / Avg: 488.67 / Max: 490Min: 581 / Avg: 582 / Max: 584Min: 530 / Avg: 570.67 / Max: 599Min: 630 / Avg: 636 / Max: 642Min: 604 / Avg: 611 / Max: 625Min: 813 / Avg: 819.67 / Max: 825

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: LuxCore Benchmark - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 15SE +/- 0.03, N = 3SE +/- 0.13, N = 15SE +/- 0.06, N = 15SE +/- 0.14, N = 152.744.593.916.146.887.958.288.654.506.89MIN: 0.95 / MAX: 3.24MIN: 1.65 / MAX: 5.43MIN: 1.48 / MAX: 4.54MIN: 2.23 / MAX: 7.29MIN: 2.64 / MAX: 8.05MIN: 2.7 / MAX: 10.56MIN: 3.2 / MAX: 9.69MIN: 3.01 / MAX: 12.25MIN: 1.72 / MAX: 5.53MIN: 2.38 / MAX: 8.45
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215Min: 2.72 / Avg: 2.74 / Max: 2.76Min: 4.55 / Avg: 4.59 / Max: 4.62Min: 3.89 / Avg: 3.91 / Max: 3.92Min: 6.1 / Avg: 6.14 / Max: 6.18Min: 6.85 / Avg: 6.88 / Max: 6.9Min: 7.57 / Avg: 7.95 / Max: 8.78Min: 8.24 / Avg: 8.28 / Max: 8.34Min: 8.12 / Avg: 8.65 / Max: 10.1Min: 4.16 / Avg: 4.5 / Max: 4.8Min: 5.7 / Avg: 6.89 / Max: 7.37

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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KSE +/- 17.34, N = 3SE +/- 417.02, N = 3SE +/- 20.89, N = 3SE +/- 127.65, N = 3SE +/- 57.61, N = 3SE +/- 253.07, N = 4SE +/- 36.92, N = 3SE +/- 436.19, N = 4SE +/- 75.47, N = 3SE +/- 74.38, N = 436870.6768019.8936773.0271183.8051957.16114285.7452123.90115068.8337645.4192499.871. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KMin: 36851.96 / Avg: 36870.67 / Max: 36905.31Min: 67516.98 / Avg: 68019.89 / Max: 68847.57Min: 36739.27 / Avg: 36773.02 / Max: 36811.22Min: 71000.81 / Avg: 71183.8 / Max: 71429.48Min: 51847.85 / Avg: 51957.16 / Max: 52043.36Min: 113820.3 / Avg: 114285.74 / Max: 114991.54Min: 52066.65 / Avg: 52123.9 / Max: 52192.91Min: 113849.86 / Avg: 115068.83 / Max: 115904.31Min: 37495.49 / Avg: 37645.41 / Max: 37735.55Min: 92296.12 / Avg: 92499.87 / Max: 92623.781. (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.BEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030K60K90K120K150KSE +/- 80.29, N = 5SE +/- 499.63, N = 7SE +/- 86.86, N = 6SE +/- 235.51, N = 7SE +/- 693.60, N = 7SE +/- 1054.88, N = 11SE +/- 524.95, N = 7SE +/- 1164.34, N = 9SE +/- 122.82, N = 6SE +/- 276.83, N = 946716.5790510.8147458.8795708.0690434.68142813.7291716.95145772.3150133.58123538.141. (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.BEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030K60K90K120K150KMin: 46459.52 / Avg: 46716.57 / Max: 46943.73Min: 88108.75 / Avg: 90510.81 / Max: 92500.48Min: 47146.86 / Avg: 47458.87 / Max: 47707.19Min: 94739.1 / Avg: 95708.06 / Max: 96576.64Min: 86413.72 / Avg: 90434.68 / Max: 91500.79Min: 137729.63 / Avg: 142813.72 / Max: 147468.06Min: 89797.14 / Avg: 91716.95 / Max: 93453.83Min: 138252.96 / Avg: 145772.31 / Max: 149182.87Min: 49878.03 / Avg: 50133.58 / Max: 50710Min: 122516.28 / Avg: 123538.14 / Max: 124751.691. (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

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 30MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801020304050SE +/- 0.04, N = 3SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.25, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 339.2343.5928.4617.9521.0216.0819.7815.3323.4914.301. (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 30MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380918273645Min: 39.15 / Avg: 39.23 / Max: 39.29Min: 42.69 / Avg: 43.59 / Max: 44.24Min: 28.26 / Avg: 28.46 / Max: 28.66Min: 17.75 / Avg: 17.95 / Max: 18.05Min: 20.83 / Avg: 21.02 / Max: 21.19Min: 15.77 / Avg: 16.08 / Max: 16.47Min: 19.68 / Avg: 19.78 / Max: 19.86Min: 13.08 / Avg: 15.33 / Max: 16.51Min: 23.46 / Avg: 23.49 / Max: 23.53Min: 14.27 / Avg: 14.3 / Max: 14.361. (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

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: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380700M1400M2100M2800M3500MSE +/- 1266666.67, N = 3SE +/- 218581.28, N = 3SE +/- 1117039.74, N = 3SE +/- 5833619.04, N = 3SE +/- 3315116.89, N = 3SE +/- 17236814.61, N = 3SE +/- 3319805.88, N = 3SE +/- 6756313.92, N = 3SE +/- 1039764.93, N = 3SE +/- 4053941.84, N = 310204333332030033333143093333326887666672590700000283063333329269333333091333333165406666730473333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380500M1000M1500M2000M2500MMin: 1018700000 / Avg: 1020433333.33 / Max: 1022900000Min: 2029600000 / Avg: 2030033333.33 / Max: 2030300000Min: 1428700000 / Avg: 1430933333.33 / Max: 1432100000Min: 2677700000 / Avg: 2688766666.67 / Max: 2697500000Min: 2585400000 / Avg: 2590700000 / Max: 2596800000Min: 2812800000 / Avg: 2830633333.33 / Max: 2865100000Min: 2922800000 / Avg: 2926933333.33 / Max: 2933500000Min: 3079500000 / Avg: 3091333333.33 / Max: 3102900000Min: 1652300000 / Avg: 1654066666.67 / Max: 1655900000Min: 3039300000 / Avg: 3047333333.33 / Max: 30523000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 DirectionEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240SE +/- 0.02, N = 3SE +/- 0.15, N = 15SE +/- 0.21, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 4SE +/- 0.07, N = 3SE +/- 0.04, N = 4SE +/- 0.01, N = 3SE +/- 0.02, N = 433.4718.0130.0416.4022.1511.2121.9911.1224.0411.061. (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
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 33.46 / Avg: 33.47 / Max: 33.51Min: 16.56 / Avg: 18.01 / Max: 18.5Min: 29.63 / Avg: 30.04 / Max: 30.25Min: 16.15 / Avg: 16.4 / Max: 16.55Min: 21.96 / Avg: 22.15 / Max: 22.3Min: 11.08 / Avg: 11.21 / Max: 11.36Min: 21.85 / Avg: 21.99 / Max: 22.08Min: 11.02 / Avg: 11.12 / Max: 11.22Min: 24.03 / Avg: 24.04 / Max: 24.06Min: 11.02 / Avg: 11.06 / Max: 11.091. (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

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 BuckyballEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380120024003600480060005578.23041.44051.22177.52187.62173.92036.41914.43085.11846.81. (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

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050100150200250SE +/- 0.04, N = 3SE +/- 0.27, N = 3SE +/- 0.03, N = 3SE +/- 0.43, N = 3SE +/- 0.12, N = 3SE +/- 0.32, N = 3SE +/- 0.16, N = 3SE +/- 0.30, N = 3SE +/- 0.25, N = 3SE +/- 0.22, N = 3221.28127.83168.35102.43110.9777.69101.2873.61142.5190.57
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83804080120160200Min: 221.21 / Avg: 221.28 / Max: 221.33Min: 127.32 / Avg: 127.83 / Max: 128.25Min: 168.29 / Avg: 168.35 / Max: 168.4Min: 101.82 / Avg: 102.43 / Max: 103.25Min: 110.74 / Avg: 110.97 / Max: 111.15Min: 77.2 / Avg: 77.69 / Max: 78.29Min: 100.96 / Avg: 101.28 / Max: 101.49Min: 73.01 / Avg: 73.61 / Max: 73.97Min: 142.13 / Avg: 142.51 / Max: 142.97Min: 90.13 / Avg: 90.57 / Max: 90.81

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 AtomsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 312.0018.2616.2424.8226.0131.2729.7235.0922.6835.991. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240Min: 11.95 / Avg: 12 / Max: 12.07Min: 18.16 / Avg: 18.26 / Max: 18.35Min: 16.13 / Avg: 16.24 / Max: 16.31Min: 24.67 / Avg: 24.82 / Max: 24.94Min: 25.88 / Avg: 26.01 / Max: 26.12Min: 31.24 / Avg: 31.27 / Max: 31.3Min: 29.35 / Avg: 29.72 / Max: 30.02Min: 34.8 / Avg: 35.09 / Max: 35.36Min: 22.52 / Avg: 22.68 / Max: 22.83Min: 35.95 / Avg: 35.99 / Max: 36.041. (CXX) g++ options: -O3 -pthread -lm

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 2.5kmEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805K10K15K20K25K24803.7413171.2821447.8111194.3717010.998587.3716479.898323.1218356.469822.731. (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

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 60MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.41, N = 3SE +/- 1.33, N = 3SE +/- 0.08, N = 3SE +/- 0.66, N = 3SE +/- 0.04, N = 3SE +/- 0.22, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 3263.64152.36264.46136.13205.3092.61204.5889.83224.58103.611. (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 60MEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838050100150200250Min: 263.38 / Avg: 263.64 / Max: 263.89Min: 152.17 / Avg: 152.36 / Max: 152.52Min: 263.86 / Avg: 264.46 / Max: 265.25Min: 134.05 / Avg: 136.13 / Max: 138.6Min: 205.16 / Avg: 205.3 / Max: 205.45Min: 91.54 / Avg: 92.61 / Max: 93.81Min: 204.51 / Avg: 204.58 / Max: 204.64Min: 89.57 / Avg: 89.83 / Max: 90.26Min: 224.44 / Avg: 224.58 / Max: 224.83Min: 103.52 / Avg: 103.61 / Max: 103.691. (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

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 V4EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380300K600K900K1200K1500KSE +/- 342.75, N = 3SE +/- 6672.77, N = 3SE +/- 1076.71, N = 3SE +/- 10479.24, N = 3SE +/- 4082.38, N = 3SE +/- 8050.46, N = 15SE +/- 856.80, N = 3SE +/- 7142.63, N = 15SE +/- 1036.96, N = 3SE +/- 2539.56, N = 3154242397028812606308700346728595531286446435274721178463666967
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380300K600K900K1200K1500KMin: 1541780 / Avg: 1542423.33 / Max: 1542950Min: 960163 / Avg: 970288.33 / Max: 982880Min: 1259450 / Avg: 1260630 / Max: 1262780Min: 855768 / Avg: 870034.33 / Max: 890464Min: 665402 / Avg: 672859.33 / Max: 679467Min: 518719 / Avg: 553128.4 / Max: 626206Min: 642948 / Avg: 644642.67 / Max: 645710Min: 500571 / Avg: 527472 / Max: 585597Min: 1176530 / Avg: 1178463.33 / Max: 1180080Min: 662334 / Avg: 666967.33 / Max: 671086

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 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801428425670SE +/- 0.20, N = 7SE +/- 0.18, N = 8SE +/- 0.23, N = 6SE +/- 0.32, N = 3SE +/- 0.73, N = 15SE +/- 1.14, N = 12SE +/- 0.38, N = 15SE +/- 0.43, N = 15SE +/- 0.05, N = 3SE +/- 0.11, N = 421.5321.7223.4922.6255.6056.8361.2862.0721.8057.421. (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 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801224364860Min: 20.35 / Avg: 21.53 / Max: 21.89Min: 20.56 / Avg: 21.72 / Max: 22.21Min: 22.33 / Avg: 23.49 / Max: 23.82Min: 21.98 / Avg: 22.62 / Max: 22.95Min: 45.45 / Avg: 55.6 / Max: 56.87Min: 44.44 / Avg: 56.83 / Max: 58.87Min: 56.14 / Avg: 61.28 / Max: 62.39Min: 56.73 / Avg: 62.07 / Max: 63.56Min: 21.7 / Avg: 21.8 / Max: 21.86Min: 57.12 / Avg: 57.42 / Max: 57.611. (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: FT.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030K60K90K120K150KSE +/- 100.97, N = 5SE +/- 593.91, N = 10SE +/- 71.08, N = 5SE +/- 551.79, N = 6SE +/- 91.52, N = 5SE +/- 606.97, N = 6SE +/- 95.78, N = 5SE +/- 391.79, N = 6SE +/- 41.49, N = 6SE +/- 106.40, N = 743155.2878574.0044870.9982082.4360492.26116003.8462384.37120465.5057275.08100812.541. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KMin: 42926.5 / Avg: 43155.28 / Max: 43527.2Min: 76360.73 / Avg: 78574 / Max: 82255.98Min: 44711.18 / Avg: 44870.99 / Max: 45089.12Min: 80429.71 / Avg: 82082.43 / Max: 84265.72Min: 60282.83 / Avg: 60492.26 / Max: 60715.41Min: 113542.33 / Avg: 116003.84 / Max: 117699.08Min: 62014.01 / Avg: 62384.37 / Max: 62551.59Min: 119025.16 / Avg: 120465.5 / Max: 121810.92Min: 57137.47 / Avg: 57275.08 / Max: 57377.23Min: 100490.94 / Avg: 100812.54 / Max: 101268.271. (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

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 3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 4SE +/- 0.01, N = 4SE +/- 0.07, N = 4SE +/- 0.00, N = 4SE +/- 0.05, N = 5SE +/- 0.01, N = 3SE +/- 0.04, N = 431.5218.9623.9115.1415.7011.5814.8411.3422.8715.511. (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 3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 31.51 / Avg: 31.52 / Max: 31.53Min: 18.92 / Avg: 18.96 / Max: 19Min: 23.89 / Avg: 23.91 / Max: 23.93Min: 15.08 / Avg: 15.14 / Max: 15.21Min: 15.68 / Avg: 15.7 / Max: 15.74Min: 11.4 / Avg: 11.57 / Max: 11.72Min: 14.83 / Avg: 14.84 / Max: 14.85Min: 11.2 / Avg: 11.34 / Max: 11.45Min: 22.85 / Avg: 22.87 / Max: 22.88Min: 15.45 / Avg: 15.51 / Max: 15.611. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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.i3dEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802004006008001000SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 2.21, N = 3SE +/- 0.74, N = 3SE +/- 0.23, N = 3SE +/- 1.38, N = 3SE +/- 0.09, N = 3SE +/- 0.44, N = 3SE +/- 1.61, N = 3792.63405.10716.36360.79608.23299.09602.97297.68554.94291.421. (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.i3dEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380140280420560700Min: 792.5 / Avg: 792.63 / Max: 792.85Min: 405.06 / Avg: 405.1 / Max: 405.16Min: 716.26 / Avg: 716.36 / Max: 716.54Min: 356.38 / Avg: 360.79 / Max: 363.07Min: 606.76 / Avg: 608.23 / Max: 609.06Min: 298.75 / Avg: 299.09 / Max: 299.53Min: 601.48 / Avg: 602.97 / Max: 605.73Min: 297.56 / Avg: 297.68 / Max: 297.84Min: 554.07 / Avg: 554.94 / Max: 555.49Min: 289.27 / Avg: 291.42 / Max: 294.571. (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

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 SolverEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215SE +/- 0.044, N = 4SE +/- 0.077, N = 5SE +/- 0.015, N = 5SE +/- 0.114, N = 15SE +/- 0.006, N = 6SE +/- 0.022, N = 7SE +/- 0.017, N = 6SE +/- 0.049, N = 9SE +/- 0.007, N = 7SE +/- 0.024, N = 812.8059.7079.9568.4286.7476.0496.5166.1406.2114.7091. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620Min: 12.67 / Avg: 12.8 / Max: 12.87Min: 9.56 / Avg: 9.71 / Max: 9.98Min: 9.9 / Avg: 9.96 / Max: 9.98Min: 7.83 / Avg: 8.43 / Max: 9.09Min: 6.72 / Avg: 6.75 / Max: 6.76Min: 5.99 / Avg: 6.05 / Max: 6.13Min: 6.46 / Avg: 6.52 / Max: 6.56Min: 5.83 / Avg: 6.14 / Max: 6.28Min: 6.19 / Avg: 6.21 / Max: 6.25Min: 4.62 / Avg: 4.71 / Max: 4.861. (CXX) g++ options: -O2 -lOpenCL

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 4 - Input: Bosphorus 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801.13652.2733.40954.5465.6825SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.007, N = 3SE +/- 0.059, N = 3SE +/- 0.051, N = 5SE +/- 0.022, N = 3SE +/- 0.049, N = 3SE +/- 0.007, N = 3SE +/- 0.036, N = 31.9721.9972.1182.0794.7884.8075.0515.0501.8594.7341. (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 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810Min: 1.97 / Avg: 1.97 / Max: 1.98Min: 1.99 / Avg: 2 / Max: 2Min: 2.12 / Avg: 2.12 / Max: 2.12Min: 2.07 / Avg: 2.08 / Max: 2.09Min: 4.68 / Avg: 4.79 / Max: 4.88Min: 4.62 / Avg: 4.81 / Max: 4.9Min: 5.01 / Avg: 5.05 / Max: 5.08Min: 4.98 / Avg: 5.05 / Max: 5.14Min: 1.85 / Avg: 1.86 / Max: 1.87Min: 4.67 / Avg: 4.73 / Max: 4.81. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 MaterialEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380306090120150128.6069.1895.7754.2962.0251.1056.0447.8277.5257.40

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 ProteinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835SE +/- 0.05, N = 10SE +/- 0.12, N = 12SE +/- 0.10, N = 10SE +/- 0.32, N = 15SE +/- 0.33, N = 15SE +/- 0.32, N = 15SE +/- 0.29, N = 15SE +/- 0.34, N = 15SE +/- 0.23, N = 15SE +/- 0.33, N = 1511.9516.3715.6523.1522.5428.0524.8830.9620.8431.561. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 11.67 / Avg: 11.95 / Max: 12.11Min: 15.61 / Avg: 16.37 / Max: 16.78Min: 15.2 / Avg: 15.65 / Max: 16.15Min: 21.26 / Avg: 23.15 / Max: 24.94Min: 20.81 / Avg: 22.54 / Max: 24.7Min: 26.55 / Avg: 28.05 / Max: 31.2Min: 23.91 / Avg: 24.88 / Max: 27.59Min: 29.16 / Avg: 30.95 / Max: 33.2Min: 19.02 / Avg: 20.84 / Max: 22.16Min: 29.36 / Avg: 31.56 / Max: 33.911. (CXX) g++ options: -O3 -pthread -lm

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801122334455SE +/- 0.53, N = 3SE +/- 0.37, N = 4SE +/- 0.44, N = 3SE +/- 0.24, N = 6SE +/- 0.21, N = 9SE +/- 0.16, N = 12SE +/- 0.20, N = 8SE +/- 0.14, N = 13SE +/- 0.41, N = 3SE +/- 0.24, N = 548.4729.9737.4724.2526.3219.5624.3518.6332.0121.63
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801020304050Min: 47.88 / Avg: 48.46 / Max: 49.52Min: 29.57 / Avg: 29.97 / Max: 31.07Min: 37.02 / Avg: 37.47 / Max: 38.35Min: 23.99 / Avg: 24.25 / Max: 25.45Min: 26.01 / Avg: 26.32 / Max: 27.99Min: 19.27 / Avg: 19.56 / Max: 21.34Min: 24.06 / Avg: 24.35 / Max: 25.75Min: 18.39 / Avg: 18.63 / Max: 20.35Min: 31.57 / Avg: 32.01 / Max: 32.84Min: 21.36 / Avg: 21.63 / Max: 22.58

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: CG.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838011K22K33K44K55KSE +/- 75.84, N = 6SE +/- 1105.03, N = 15SE +/- 132.68, N = 6SE +/- 1312.75, N = 15SE +/- 98.38, N = 6SE +/- 396.43, N = 15SE +/- 116.19, N = 6SE +/- 628.54, N = 15SE +/- 41.74, N = 6SE +/- 84.43, N = 819753.5432439.0621383.5532040.7624472.5844800.9224861.3449508.6322890.2540188.841. (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: CG.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83809K18K27K36K45KMin: 19491.67 / Avg: 19753.54 / Max: 20008.88Min: 26412.12 / Avg: 32439.06 / Max: 37518.44Min: 21064.63 / Avg: 21383.55 / Max: 21937.45Min: 25167.94 / Avg: 32040.76 / Max: 39946.3Min: 24116.02 / Avg: 24472.58 / Max: 24749.72Min: 42068.76 / Avg: 44800.92 / Max: 48360.1Min: 24494.39 / Avg: 24861.34 / Max: 25237.64Min: 45857.85 / Avg: 49508.63 / Max: 52316.94Min: 22770.31 / Avg: 22890.25 / Max: 23050.34Min: 39926.53 / Avg: 40188.84 / Max: 40553.931. (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.DEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838010002000300040005000SE +/- 6.87, N = 3SE +/- 19.06, N = 3SE +/- 0.57, N = 3SE +/- 24.48, N = 4SE +/- 9.73, N = 4SE +/- 52.78, N = 15SE +/- 20.96, N = 4SE +/- 40.27, N = 4SE +/- 6.51, N = 3SE +/- 20.88, N = 41894.632849.371895.912911.742531.764340.432563.804511.042333.563086.241. (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.DEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83808001600240032004000Min: 1885.11 / Avg: 1894.63 / Max: 1907.97Min: 2819.67 / Avg: 2849.37 / Max: 2884.9Min: 1894.86 / Avg: 1895.91 / Max: 1896.83Min: 2881.46 / Avg: 2911.74 / Max: 2984.13Min: 2502.8 / Avg: 2531.76 / Max: 2544.54Min: 4015.27 / Avg: 4340.43 / Max: 4662.37Min: 2520.37 / Avg: 2563.8 / Max: 2617.23Min: 4457.13 / Avg: 4511.04 / Max: 4630.93Min: 2321.6 / Avg: 2333.56 / Max: 2343.98Min: 3048.86 / Avg: 3086.24 / Max: 3140.911. (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: SqueezeNetEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KSE +/- 36.10, N = 3SE +/- 769.20, N = 3SE +/- 99.17, N = 3SE +/- 590.85, N = 3SE +/- 33.66, N = 3SE +/- 831.78, N = 15SE +/- 144.48, N = 3SE +/- 989.83, N = 15SE +/- 65.86, N = 3SE +/- 433.14, N = 7108729.076346.884986.061531.051560.150330.751608.351986.780455.747974.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KMin: 108662 / Avg: 108728.67 / Max: 108786Min: 75215.5 / Avg: 76346.8 / Max: 77815.3Min: 84831.6 / Avg: 84985.97 / Max: 85171Min: 60360.4 / Avg: 61531.03 / Max: 62256.1Min: 51492.8 / Avg: 51560.1 / Max: 51595.4Min: 45286.9 / Avg: 50330.7 / Max: 57283.6Min: 51393.9 / Avg: 51608.33 / Max: 51883.3Min: 45376.9 / Avg: 51986.74 / Max: 58848Min: 80352.2 / Avg: 80455.67 / Max: 80578Min: 47185.6 / Avg: 47974.57 / Max: 50234.5

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 1.2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380400M800M1200M1600M2000MSE +/- 376033.81, N = 5SE +/- 3743761.40, N = 4SE +/- 783587.66, N = 4SE +/- 15101080.25, N = 3SE +/- 1996390.54, N = 3SE +/- 1475421.56, N = 3SE +/- 508688.84, N = 3SE +/- 3070209.17, N = 3SE +/- 408650.35, N = 3SE +/- 1152755.01, N = 392352816016472127509208428751682704333994860367191380433310126330001926452000108441166720821033331. (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 1.2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380400M800M1200M1600M2000MMin: 922813600 / Avg: 923528160 / Max: 924772800Min: 1637064000 / Avg: 1647212750 / Max: 1654431000Min: 919287600 / Avg: 920842875 / Max: 922911200Min: 1657782000 / Avg: 1682704333.33 / Max: 1709940000Min: 991803500 / Avg: 994860366.67 / Max: 998613300Min: 1911220000 / Avg: 1913804333.33 / Max: 1916330000Min: 1012029000 / Avg: 1012633000 / Max: 1013644000Min: 1921804000 / Avg: 1926452000 / Max: 1932251000Min: 1083601000 / Avg: 1084411666.67 / Max: 1084907000Min: 2080897000 / Avg: 2082103333.33 / Max: 20844080001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi

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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838030K60K90K120K150KSE +/- 85.38, N = 8SE +/- 386.86, N = 9SE +/- 142.47, N = 8SE +/- 363.89, N = 9SE +/- 185.04, N = 7SE +/- 395.58, N = 7SE +/- 176.84, N = 7SE +/- 294.94, N = 7SE +/- 182.12, N = 9SE +/- 268.68, N = 1153570.3286413.6353096.6185423.7957387.14101537.0558310.45101849.5556287.53118831.521. (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.CEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KMin: 53034.85 / Avg: 53570.32 / Max: 53829.22Min: 84802.39 / Avg: 86413.63 / Max: 88142.72Min: 52501.13 / Avg: 53096.61 / Max: 53654.94Min: 83793.63 / Avg: 85423.79 / Max: 87050.74Min: 56647.69 / Avg: 57387.14 / Max: 58047.23Min: 99546.46 / Avg: 101537.05 / Max: 102763.6Min: 57737.17 / Avg: 58310.45 / Max: 59049.08Min: 100717.47 / Avg: 101849.55 / Max: 102702.75Min: 55378.33 / Avg: 56287.53 / Max: 56977.9Min: 117326.18 / Avg: 118831.52 / Max: 119978.831. (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

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 FastEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801326395265SE +/- 0.24, N = 7SE +/- 0.21, N = 15SE +/- 0.24, N = 9SE +/- 0.37, N = 8SE +/- 0.45, N = 4SE +/- 0.34, N = 14SE +/- 0.12, N = 4SE +/- 0.52, N = 6SE +/- 0.02, N = 3SE +/- 0.19, N = 426.0938.6729.8544.8536.8351.4740.2755.8427.5738.711. (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 FastEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801122334455Min: 24.68 / Avg: 26.09 / Max: 26.38Min: 35.84 / Avg: 38.67 / Max: 39.17Min: 27.96 / Avg: 29.85 / Max: 30.16Min: 42.26 / Avg: 44.85 / Max: 45.38Min: 35.47 / Avg: 36.83 / Max: 37.34Min: 48.16 / Avg: 51.47 / Max: 53.71Min: 39.96 / Avg: 40.27 / Max: 40.53Min: 53.51 / Avg: 55.84 / Max: 56.91Min: 27.53 / Avg: 27.57 / Max: 27.6Min: 38.36 / Avg: 38.71 / Max: 39.061. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 MakefilesEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838080160240320400SE +/- 3.69, N = 3SE +/- 2.00, N = 12SE +/- 3.00, N = 3SE +/- 0.64, N = 3SE +/- 0.11, N = 3SE +/- 1.19, N = 3SE +/- 1.32, N = 3SE +/- 0.54, N = 3SE +/- 0.72, N = 3SE +/- 0.65, N = 3374.20230.58295.31192.96216.84181.89203.22176.97256.63190.68
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070140210280350Min: 368.54 / Avg: 374.2 / Max: 381.13Min: 223.28 / Avg: 230.58 / Max: 242.06Min: 290.45 / Avg: 295.31 / Max: 300.78Min: 191.95 / Avg: 192.96 / Max: 194.14Min: 216.61 / Avg: 216.84 / Max: 216.96Min: 179.55 / Avg: 181.89 / Max: 183.42Min: 200.9 / Avg: 203.22 / Max: 205.46Min: 176.09 / Avg: 176.97 / Max: 177.96Min: 255.33 / Avg: 256.63 / Max: 257.83Min: 189.87 / Avg: 190.68 / Max: 191.98

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 3SE +/- 0.09, N = 4SE +/- 0.05, N = 3SE +/- 0.10, N = 331.1520.6524.9217.3718.9115.1517.9014.9222.3216.43
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 31.04 / Avg: 31.15 / Max: 31.27Min: 20.44 / Avg: 20.65 / Max: 20.79Min: 24.89 / Avg: 24.92 / Max: 24.96Min: 17.28 / Avg: 17.37 / Max: 17.47Min: 18.84 / Avg: 18.91 / Max: 19.03Min: 15.11 / Avg: 15.15 / Max: 15.22Min: 17.89 / Avg: 17.9 / Max: 17.91Min: 14.77 / Avg: 14.92 / Max: 15.13Min: 22.24 / Avg: 22.32 / Max: 22.42Min: 16.33 / Avg: 16.43 / Max: 16.62

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 2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620SE +/- 0.025, N = 3SE +/- 0.016, N = 4SE +/- 0.022, N = 4SE +/- 0.023, N = 5SE +/- 0.013, N = 5SE +/- 0.016, N = 5SE +/- 0.013, N = 5SE +/- 0.067, N = 5SE +/- 0.024, N = 4SE +/- 0.018, N = 418.18812.24614.48510.38110.8459.04310.5789.11414.93011.4151. (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 2EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380510152025Min: 18.16 / Avg: 18.19 / Max: 18.24Min: 12.2 / Avg: 12.25 / Max: 12.27Min: 14.44 / Avg: 14.48 / Max: 14.55Min: 10.31 / Avg: 10.38 / Max: 10.44Min: 10.8 / Avg: 10.84 / Max: 10.88Min: 8.99 / Avg: 9.04 / Max: 9.08Min: 10.56 / Avg: 10.58 / Max: 10.63Min: 9 / Avg: 9.11 / Max: 9.29Min: 14.9 / Avg: 14.93 / Max: 15Min: 11.38 / Avg: 11.41 / Max: 11.461. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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 MetricEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380700K1400K2100K2800K3500K2346574022243374755968476611923120834751934313310342332424115871. (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: GarlicoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83809K18K27K36K45KSE +/- 15.81, N = 3SE +/- 65.64, N = 3SE +/- 4.34, N = 3SE +/- 34.80, N = 3SE +/- 158.75, N = 3SE +/- 329.36, N = 3SE +/- 63.86, N = 3SE +/- 15.28, N = 3SE +/- 181.40, N = 4SE +/- 585.01, N = 153677.237661.495119.4510693.0014410.0028307.0014683.0028680.0015618.0041269.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: GarlicoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83807K14K21K28K35KMin: 3660.53 / Avg: 3677.23 / Max: 3708.83Min: 7552.86 / Avg: 7661.49 / Max: 7779.64Min: 5112.78 / Avg: 5119.45 / Max: 5127.6Min: 10630 / Avg: 10693.33 / Max: 10750Min: 14110 / Avg: 14410 / Max: 14650Min: 27750 / Avg: 28306.67 / Max: 28890Min: 14580 / Avg: 14683.33 / Max: 14800Min: 28660 / Avg: 28680 / Max: 28710Min: 15160 / Avg: 15617.5 / Max: 16020Min: 34490 / Avg: 41268.67 / Max: 438601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380130260390520650SE +/- 1.44, N = 3SE +/- 1.64, N = 3SE +/- 2.84, N = 3SE +/- 2.26, N = 3SE +/- 2.42, N = 3SE +/- 5.27, N = 15SE +/- 1.69, N = 3SE +/- 1.79, N = 3SE +/- 0.60, N = 3SE +/- 0.65, N = 3309.95400.29397.62475.57521.07571.24558.19605.38404.27532.57MIN: 271.25 / MAX: 359.86MIN: 284.94 / MAX: 449MIN: 319.68 / MAX: 462.02MIN: 271.07 / MAX: 519.7MIN: 253.59 / MAX: 576.48MIN: 128.23 / MAX: 700.02MIN: 265.54 / MAX: 606.35MIN: 130.58 / MAX: 714.41MIN: 275.43 / MAX: 456.48MIN: 189.3 / MAX: 586.861. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Summer Nature 4KEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380110220330440550Min: 307.09 / Avg: 309.95 / Max: 311.58Min: 397.99 / Avg: 400.29 / Max: 403.46Min: 391.97 / Avg: 397.62 / Max: 400.98Min: 471.28 / Avg: 475.57 / Max: 478.94Min: 516.38 / Avg: 521.07 / Max: 524.44Min: 507.61 / Avg: 571.24 / Max: 593.58Min: 556.41 / Avg: 558.19 / Max: 561.58Min: 602.77 / Avg: 605.38 / Max: 608.8Min: 403.07 / Avg: 404.27 / Max: 404.95Min: 531.27 / Avg: 532.57 / Max: 533.361. (CC) gcc options: -pthread -lm

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.36, N = 3SE +/- 0.34, N = 3SE +/- 0.46, N = 3SE +/- 0.21, N = 3SE +/- 0.33, N = 318.0025.3422.3727.0927.2930.4232.2232.3631.0633.43
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835Min: 17.82 / Avg: 18 / Max: 18.12Min: 25.15 / Avg: 25.34 / Max: 25.56Min: 21.98 / Avg: 22.37 / Max: 22.76Min: 26.94 / Avg: 27.09 / Max: 27.32Min: 27.14 / Avg: 27.29 / Max: 27.48Min: 29.83 / Avg: 30.42 / Max: 31.07Min: 31.64 / Avg: 32.22 / Max: 32.83Min: 31.85 / Avg: 32.36 / Max: 33.28Min: 30.8 / Avg: 31.06 / Max: 31.48Min: 32.76 / Avg: 33.43 / Max: 33.8

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 3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380246810SE +/- 0.005, N = 6SE +/- 0.009, N = 7SE +/- 0.006, N = 7SE +/- 0.025, N = 8SE +/- 0.003, N = 8SE +/- 0.028, N = 8SE +/- 0.003, N = 8SE +/- 0.027, N = 8SE +/- 0.006, N = 7SE +/- 0.005, N = 87.3065.0415.8384.3784.4503.9644.3523.9696.0134.658
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215Min: 7.3 / Avg: 7.31 / Max: 7.33Min: 5.01 / Avg: 5.04 / Max: 5.09Min: 5.83 / Avg: 5.84 / Max: 5.87Min: 4.29 / Avg: 4.38 / Max: 4.52Min: 4.43 / Avg: 4.45 / Max: 4.46Min: 3.86 / Avg: 3.96 / Max: 4.07Min: 4.34 / Avg: 4.35 / Max: 4.37Min: 3.88 / Avg: 3.97 / Max: 4.08Min: 6 / Avg: 6.01 / Max: 6.05Min: 4.65 / Avg: 4.66 / Max: 4.69

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: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380918273645SE +/- 0.10, N = 3SE +/- 0.32, N = 5SE +/- 0.33, N = 3SE +/- 0.35, N = 3SE +/- 0.11, N = 3SE +/- 0.42, N = 3SE +/- 0.20, N = 3SE +/- 0.48, N = 3SE +/- 0.12, N = 3SE +/- 0.31, N = 321.7429.7828.1031.4331.9734.4637.7135.9236.9738.51
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380816243240Min: 21.55 / Avg: 21.74 / Max: 21.84Min: 28.81 / Avg: 29.78 / Max: 30.39Min: 27.66 / Avg: 28.1 / Max: 28.75Min: 30.99 / Avg: 31.43 / Max: 32.12Min: 31.76 / Avg: 31.97 / Max: 32.09Min: 33.65 / Avg: 34.46 / Max: 35.06Min: 37.5 / Avg: 37.71 / Max: 38.11Min: 34.98 / Avg: 35.92 / Max: 36.55Min: 36.81 / Avg: 36.97 / Max: 37.2Min: 38.2 / Avg: 38.51 / Max: 39.12

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 1080pEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838080160240320400SE +/- 0.18, N = 9SE +/- 1.95, N = 10SE +/- 0.47, N = 10SE +/- 1.74, N = 10SE +/- 0.91, N = 10SE +/- 2.35, N = 9SE +/- 0.84, N = 10SE +/- 2.61, N = 10SE +/- 0.54, N = 10SE +/- 2.91, N = 15197.60305.04269.51347.70320.21320.63342.80342.98290.36313.931. (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 1080pEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300Min: 196.91 / Avg: 197.6 / Max: 198.35Min: 295.86 / Avg: 305.04 / Max: 313.15Min: 267.26 / Avg: 269.51 / Max: 271.62Min: 336.51 / Avg: 347.7 / Max: 353.57Min: 316.62 / Avg: 320.21 / Max: 325.91Min: 311.53 / Avg: 320.63 / Max: 332.59Min: 339.17 / Avg: 342.8 / Max: 347.83Min: 331.49 / Avg: 342.98 / Max: 355.87Min: 288.18 / Avg: 290.36 / Max: 292.83Min: 301.51 / Avg: 313.93 / Max: 340.331. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380714212835SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 328.4219.2023.0716.8319.0016.9618.2916.8421.7918.71
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380612182430Min: 28.39 / Avg: 28.42 / Max: 28.44Min: 19.1 / Avg: 19.2 / Max: 19.25Min: 23 / Avg: 23.07 / Max: 23.11Min: 16.68 / Avg: 16.83 / Max: 17.01Min: 18.93 / Avg: 19 / Max: 19.05Min: 16.88 / Avg: 16.96 / Max: 17.03Min: 18.28 / Avg: 18.29 / Max: 18.32Min: 16.74 / Avg: 16.84 / Max: 16.94Min: 21.79 / Avg: 21.79 / Max: 21.81Min: 18.56 / Avg: 18.71 / Max: 18.94

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-bitEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802004006008001000SE +/- 0.88, N = 3SE +/- 1.00, N = 3SE +/- 6.10, N = 3SE +/- 3.74, N = 3SE +/- 0.54, N = 3SE +/- 13.81, N = 3SE +/- 0.89, N = 3SE +/- 6.96, N = 3SE +/- 0.41, N = 3SE +/- 1.95, N = 3698.60743.22767.81904.48952.431003.00980.821130.16775.38861.39MIN: 527.38 / MAX: 992.58MIN: 590.5 / MAX: 971.1MIN: 571.52 / MAX: 1097.6MIN: 649.98 / MAX: 1136.38MIN: 647.77 / MAX: 1248.54MIN: 414.93 / MAX: 1239.29MIN: 674.62 / MAX: 1286.38MIN: 439.65 / MAX: 1387.5MIN: 588.21 / MAX: 1071.6MIN: 524.86 / MAX: 1144.291. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Chimera 1080p 10-bitEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802004006008001000Min: 697.26 / Avg: 698.6 / Max: 700.26Min: 741.87 / Avg: 743.22 / Max: 745.18Min: 761.66 / Avg: 767.81 / Max: 780Min: 900.44 / Avg: 904.48 / Max: 911.95Min: 951.67 / Avg: 952.43 / Max: 953.47Min: 986.15 / Avg: 1003 / Max: 1030.38Min: 979.43 / Avg: 980.82 / Max: 982.49Min: 1117.75 / Avg: 1130.16 / Max: 1141.82Min: 774.63 / Avg: 775.38 / Max: 776.04Min: 857.51 / Avg: 861.39 / Max: 863.721. (CC) gcc options: -pthread -lm

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: vklBenchmarkVdbVolumeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83806M12M18M24M30MSE +/- 28544.62, N = 3SE +/- 155839.54, N = 3SE +/- 152393.23, N = 3SE +/- 172811.00, N = 9SE +/- 30869.23, N = 3SE +/- 84378.25, N = 3SE +/- 226481.70, N = 3SE +/- 6774.62, N = 3SE +/- 65507.38, N = 3SE +/- 89609.36, N = 318357337195460572073010921418616231019982264515723768667233264422909215529143044MIN: 949764 / MAX: 91802808MIN: 945547 / MAX: 89885088MIN: 961599 / MAX: 99737712MIN: 958352 / MAX: 128064384MIN: 877921 / MAX: 126651384MIN: 863160 / MAX: 123373224MIN: 833206 / MAX: 134771328MIN: 836796 / MAX: 130249584MIN: 1047483 / MAX: 175929480MIN: 1069452 / MAX: 176387184
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolumeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83805M10M15M20M25MMin: 18312669 / Avg: 18357337 / Max: 18410460Min: 19347348 / Avg: 19546056.67 / Max: 19853363Min: 20426096 / Avg: 20730109 / Max: 20900908Min: 21043039 / Avg: 21418615.67 / Max: 22705818Min: 23053101 / Avg: 23101997.67 / Max: 23159089Min: 22543506 / Avg: 22645157.33 / Max: 22812642Min: 23371129 / Avg: 23768667 / Max: 24155464Min: 23314050 / Avg: 23326442 / Max: 23337383Min: 28968038 / Avg: 29092154.67 / Max: 29190544Min: 28965041 / Avg: 29143044 / Max: 29250093

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020406080100SE +/- 0.02, N = 3SE +/- 0.42, N = 3SE +/- 0.05, N = 3SE +/- 0.33, N = 3SE +/- 0.13, N = 3SE +/- 0.31, N = 3SE +/- 0.10, N = 3SE +/- 0.35, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 375.7354.8960.9548.6551.2854.6248.6551.4456.5848.07
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801530456075Min: 75.7 / Avg: 75.73 / Max: 75.76Min: 54.42 / Avg: 54.89 / Max: 55.73Min: 60.89 / Avg: 60.95 / Max: 61.06Min: 48.07 / Avg: 48.65 / Max: 49.2Min: 51.05 / Avg: 51.28 / Max: 51.49Min: 54.01 / Avg: 54.62 / Max: 54.99Min: 48.51 / Avg: 48.65 / Max: 48.85Min: 50.85 / Avg: 51.44 / Max: 52.07Min: 56.27 / Avg: 56.58 / Max: 56.9Min: 47.95 / Avg: 48.07 / Max: 48.23

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620SE +/- 0.03, N = 3SE +/- 0.09, N = 4SE +/- 0.11, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 4SE +/- 0.09, N = 4SE +/- 0.09, N = 4SE +/- 0.06, N = 4SE +/- 0.06, N = 4SE +/- 0.14, N = 416.9812.8014.6511.8312.8911.5912.6111.6914.3711.96
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620Min: 16.95 / Avg: 16.98 / Max: 17.04Min: 12.57 / Avg: 12.8 / Max: 12.97Min: 14.38 / Avg: 14.65 / Max: 14.94Min: 11.73 / Avg: 11.83 / Max: 11.93Min: 12.82 / Avg: 12.89 / Max: 12.97Min: 11.36 / Avg: 11.59 / Max: 11.8Min: 12.41 / Avg: 12.61 / Max: 12.83Min: 11.59 / Avg: 11.69 / Max: 11.84Min: 14.23 / Avg: 14.37 / Max: 14.5Min: 11.56 / Avg: 11.96 / Max: 12.2

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 19EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83803691215SE +/- 0.008, N = 4SE +/- 0.054, N = 5SE +/- 0.025, N = 4SE +/- 0.077, N = 5SE +/- 0.012, N = 5SE +/- 0.034, N = 5SE +/- 0.033, N = 5SE +/- 0.035, N = 5SE +/- 0.026, N = 5SE +/- 0.024, N = 513.03310.95611.64810.33310.57410.03410.64410.24610.3879.111
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19EPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838048121620Min: 13.02 / Avg: 13.03 / Max: 13.05Min: 10.81 / Avg: 10.96 / Max: 11.14Min: 11.6 / Avg: 11.65 / Max: 11.7Min: 10.11 / Avg: 10.33 / Max: 10.57Min: 10.54 / Avg: 10.57 / Max: 10.61Min: 9.95 / Avg: 10.03 / Max: 10.11Min: 10.57 / Avg: 10.64 / Max: 10.76Min: 10.17 / Avg: 10.25 / Max: 10.37Min: 10.32 / Avg: 10.39 / Max: 10.47Min: 9.03 / Avg: 9.11 / Max: 9.16

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: vklBenchmarkStructuredVolumeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020M40M60M80M100MSE +/- 890168.25, N = 4SE +/- 856742.77, N = 15SE +/- 1376326.08, N = 3SE +/- 1150375.14, N = 15SE +/- 647652.54, N = 3SE +/- 778312.95, N = 15SE +/- 1090987.41, N = 3SE +/- 977702.28, N = 15SE +/- 47834.23, N = 3SE +/- 177762.64, N = 3797922789180995695662172100544290111275915105230162112688229109964907105023963104922070MIN: 1101918 / MAX: 843319872MIN: 1069845 / MAX: 1023983856MIN: 1102685 / MAX: 967134312MIN: 1086676 / MAX: 1172876616MIN: 1010064 / MAX: 1240796448MIN: 965186 / MAX: 1224900288MIN: 953075 / MAX: 1216612152MIN: 945854 / MAX: 1318864680MIN: 1379843 / MAX: 899785764MIN: 1391949 / MAX: 891929412
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolumeEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020M40M60M80M100MMin: 77267847 / Avg: 79792277.5 / Max: 81419380Min: 87346501 / Avg: 91809955.53 / Max: 97838034Min: 93379272 / Avg: 95662172 / Max: 98135574Min: 92310288 / Avg: 100544289.8 / Max: 108531524Min: 110616685 / Avg: 111275915.33 / Max: 112571151Min: 98374384 / Avg: 105230162 / Max: 110316147Min: 111408986 / Avg: 112688229.33 / Max: 114858672Min: 100264301 / Avg: 109964906.6 / Max: 114051887Min: 104937888 / Avg: 105023963.33 / Max: 105103162Min: 104568472 / Avg: 104922069.67 / Max: 105130887

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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83801020304050SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 342.3537.0738.2436.4040.9642.2940.5841.5837.6837.691. (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 CompileEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380918273645Min: 42.16 / Avg: 42.35 / Max: 42.68Min: 36.95 / Avg: 37.07 / Max: 37.31Min: 38.01 / Avg: 38.24 / Max: 38.59Min: 35.95 / Avg: 36.4 / Max: 36.75Min: 40.89 / Avg: 40.96 / Max: 41.03Min: 42.02 / Avg: 42.29 / Max: 42.49Min: 40.33 / Avg: 40.58 / Max: 40.96Min: 41.22 / Avg: 41.58 / Max: 41.95Min: 37.35 / Avg: 37.68 / Max: 37.98Min: 37.43 / Avg: 37.69 / Max: 37.911. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380100200300400500Min: 32.64 / Avg: 108.3 / Max: 174.48Min: 36.48 / Avg: 264.31 / Max: 373.2Min: 31.14 / Avg: 145.52 / Max: 194.5Min: 34.92 / Avg: 275.62 / Max: 386.96Min: 20.24 / Avg: 166.75 / Max: 354Min: 45.5 / Avg: 308.99 / Max: 460.33Min: 20.5 / Avg: 184.08 / Max: 286.93Min: 41.39 / Avg: 325.36 / Max: 574.02Min: 41.61 / Avg: 216.49 / Max: 291.37Min: 46.98 / Avg: 411.36 / Max: 582.07

Cpuminer-Opt

OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.15.5CPU Power Consumption MonitorEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838060120180240300Min: 34.18 / Avg: 97.07 / Max: 108.68Min: 73.44 / Avg: 153.13 / Max: 190.7Min: 32.1 / Avg: 88.75 / Max: 102.78Min: 70.47 / Avg: 147.5 / Max: 172.86Min: 39.59 / Avg: 108.54 / Max: 128.42Min: 87.46 / Avg: 164.48 / Max: 183.68Min: 37.52 / Avg: 105.08 / Max: 131.26Min: 83.22 / Avg: 153.81 / Max: 169.72Min: 42.77 / Avg: 121.17 / Max: 217.91Min: 85.42 / Avg: 265.82 / Max: 349.43

OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.15.5Algorithm: SkeincoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83802K4K6K8K10K2192.142858.683359.334345.705793.416604.445951.277924.513363.002912.41

OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.15.5CPU Power Consumption MonitorEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838070140210280350Min: 34.3 / Avg: 99.36 / Max: 160.77Min: 73.36 / Avg: 158.27 / Max: 336.33Min: 32.34 / Avg: 95.34 / Max: 132.31Min: 70.54 / Avg: 157.97 / Max: 304.6Min: 39.5 / Avg: 109.75 / Max: 142.26Min: 89.36 / Avg: 176.6 / Max: 261.52Min: 37.62 / Avg: 106.36 / Max: 136.32Min: 82.27 / Avg: 165.65 / Max: 245.53Min: 43.91 / Avg: 150.49 / Max: 248.88Min: 86.63 / Avg: 296.59 / Max: 405.01

OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.15.5Algorithm: DeepcoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380150300450600750194.44190.51304.04327.10600.10604.59637.61681.69223.16253.08

OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.15.5CPU Power Consumption MonitorEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838090180270360450Min: 34.38 / Avg: 113.14 / Max: 166.36Min: 72.38 / Avg: 215.52 / Max: 326.43Min: 31.96 / Avg: 110.2 / Max: 147.46Min: 69.95 / Avg: 218.57 / Max: 373.7Min: 39.59 / Avg: 120.43 / Max: 198.07Min: 88.63 / Avg: 220.64 / Max: 402.62Min: 37.6 / Avg: 119.47 / Max: 192.91Min: 81.99 / Avg: 214.85 / Max: 345.84Min: 44.48 / Avg: 230.09 / Max: 290.85Min: 87.98 / Avg: 411.4 / Max: 523.4

OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.15.5Algorithm: MagiEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 83807142128357.3217.60810.68510.99220.32625.14321.89628.3135.8538.877

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: SkeincoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380300K600K900K1200K1500KSE +/- 1659.73, N = 3SE +/- 3183.32, N = 15SE +/- 4018.70, N = 3SE +/- 5213.79, N = 3SE +/- 7057.60, N = 3SE +/- 19590.53, N = 15SE +/- 9553.46, N = 13SE +/- 12126.32, N = 6SE +/- 23435.25, N = 12SE +/- 19372.86, N = 12212790437750298157640993628793108629962538112188484075027741631. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: SkeincoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 8380200K400K600K800K1000KMin: 209600 / Avg: 212790 / Max: 215180Min: 400660 / Avg: 437750 / Max: 448470Min: 291670 / Avg: 298156.67 / Max: 305510Min: 635660 / Avg: 640993.33 / Max: 651420Min: 614880 / Avg: 628793.33 / Max: 637810Min: 996540 / Avg: 1086299.33 / Max: 1254810Min: 514300 / Avg: 625380.77 / Max: 648900Min: 1196230 / Avg: 1218848.33 / Max: 1267230Min: 246090 / Avg: 407501.67 / Max: 506700Min: 611710 / Avg: 774163.33 / Max: 8628801. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: DeepcoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KSE +/- 136.50, N = 3SE +/- 138.72, N = 3SE +/- 371.77, N = 3SE +/- 143.33, N = 3SE +/- 277.03, N = 3SE +/- 1091.55, N = 3SE +/- 245.65, N = 3SE +/- 2099.66, N = 15SE +/- 1301.01, N = 15SE +/- 2190.61, N = 1519320301532898751673658631067736781711291833583750611. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: DeepcoinEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838020K40K60K80K100KMin: 19150 / Avg: 19320 / Max: 19590Min: 29920 / Avg: 30153.33 / Max: 30400Min: 28600 / Avg: 28986.67 / Max: 29730Min: 51530 / Avg: 51673.33 / Max: 51960Min: 65330 / Avg: 65863.33 / Max: 66260Min: 105540 / Avg: 106773.33 / Max: 108950Min: 67380 / Avg: 67816.67 / Max: 68230Min: 101810 / Avg: 112918 / Max: 128090Min: 28420 / Avg: 33583.33 / Max: 44000Min: 54420 / Avg: 75061.33 / Max: 866601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: MagiEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838013002600390052006500SE +/- 3.98, N = 3SE +/- 4.76, N = 3SE +/- 12.63, N = 13SE +/- 43.10, N = 13SE +/- 60.18, N = 12SE +/- 20.83, N = 3SE +/- 73.06, N = 15SE +/- 43.35, N = 12SE +/- 12.34, N = 15SE +/- 39.37, N = 15828.261639.581177.542402.652447.835547.672615.926083.021346.633651.801. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: MagiEPYC 73432 x EPYC 7343EPYC 74432 x EPYC 7443EPYC 77132 x EPYC 7713EPYC 77632 x EPYC 7763Xeon Platinum 83802 x Xeon Platinum 838011002200330044005500Min: 821.53 / Avg: 828.26 / Max: 835.31Min: 1630.53 / Avg: 1639.58 / Max: 1646.64Min: 1151.78 / Avg: 1177.54 / Max: 1325.89Min: 2303.36 / Avg: 2402.65 / Max: 2894.19Min: 2243.68 / Avg: 2447.83 / Max: 2804.98Min: 5509.99 / Avg: 5547.67 / Max: 5581.88Min: 2353.98 / Avg: 2615.92 / Max: 3263.37Min: 5873.87 / Avg: 6083.02 / Max: 6489.46Min: 1307.01 / Avg: 1346.63 / Max: 1449.63Min: 3211.65 / Avg: 3651.8 / Max: 3805.31. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

122 Results Shown

oneDNN
Cpuminer-Opt
oneDNN
ACES DGEMM
NAS Parallel Benchmarks
Cpuminer-Opt
Stockfish
toyBrot Fractal Generator
Blender
Facebook RocksDB
Aircrack-ng
C-Ray
asmFish
toyBrot Fractal Generator
NAS Parallel Benchmarks
John The Ripper
ASTC Encoder
Liquid-DSP
toyBrot Fractal Generator
m-queens
Liquid-DSP
Pennant
John The Ripper
Tachyon
Pennant
Embree
Blender
Embree
NAMD
rays1bench
Primesieve
Embree
toyBrot Fractal Generator
KTX-Software toktx
Rodinia
ASKAP
Intel Open Image Denoise:
  RT.ldr_alb_nrm.3840x2160
  RT.hdr_alb_nrm.3840x2160
Blender
Intel Open Image Denoise
oneDNN
ASKAP
Xmrig
Coremark
GraphicsMagick
GROMACS
LuxCoreRender:
  DLSC - CPU
  Orange Juice - CPU
Blender
Facebook RocksDB
Helsing
7-Zip Compression
LULESH
GraphicsMagick
NAS Parallel Benchmarks
SVT-HEVC
NAS Parallel Benchmarks
Blender
oneDNN
Xmrig
Chaos Group V-RAY
Embree
TensorFlow Lite
POV-Ray
Timed LLVM Compilation
LuxCoreRender
OpenVKL
LuxCoreRender
NAS Parallel Benchmarks:
  SP.C
  SP.B
OpenFOAM
Liquid-DSP
Xcompact3d Incompact3d
NWChem
Timed Node.js Compilation
LAMMPS Molecular Dynamics Simulator
WRF
OpenFOAM
TensorFlow Lite
SVT-AV1
NAS Parallel Benchmarks
Basis Universal
Xcompact3d Incompact3d
Rodinia
SVT-AV1
Appleseed
LAMMPS Molecular Dynamics Simulator
Timed Linux Kernel Compilation
NAS Parallel Benchmarks:
  CG.C
  IS.D
TensorFlow Lite
Algebraic Multi-Grid Benchmark
NAS Parallel Benchmarks
Kvazaar
Timed LLVM Compilation
Timed FFmpeg Compilation
Basis Universal
BRL-CAD
Cpuminer-Opt
dav1d
PlaidML
KTX-Software toktx
PlaidML
SVT-HEVC
Timed Mesa Compilation
dav1d
OpenVKL
Timed Godot Game Engine Compilation
Timed ImageMagick Compilation
KTX-Software toktx
OpenVKL
Timed Wasmer Compilation
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
  Skeincoin
  CPU Power Consumption Monitor
  Deepcoin
  CPU Power Consumption Monitor
  Magi
Cpuminer-Opt:
  Skeincoin
  Deepcoin
  Magi