AMD EPYC Milan-X Mid-2022 Benchmarks

Tests for a future article. 2 x AMD EPYC 7713 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2207084-NE-FIRST755303
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
Show Result Confidence Charts

Limit displaying results to tests within:

AV1 3 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 3 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 8 Tests
C/C++ Compiler Tests 21 Tests
CPU Massive 33 Tests
Creator Workloads 28 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 4 Tests
Database Test Suite 6 Tests
Encoding 7 Tests
Fortran Tests 7 Tests
Game Development 8 Tests
Go Language Tests 2 Tests
HPC - High Performance Computing 25 Tests
Imaging 4 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 4 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Linear Algebra 2 Tests
Machine Learning 4 Tests
Molecular Dynamics 9 Tests
MPI Benchmarks 9 Tests
Multi-Core 48 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 17 Tests
Programmer / Developer System Benchmarks 11 Tests
Python 2 Tests
Raytracing 6 Tests
Renderers 8 Tests
Scientific Computing 13 Tests
Server 9 Tests
Server CPU Tests 23 Tests
Single-Threaded 3 Tests
Texture Compression 4 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 5 Tests

Statistics

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

Graph Settings

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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7713
July 05 2022
  1 Day, 11 Hours, 12 Minutes
EPYC 7713 2P
July 07 2022
  1 Day, 9 Hours, 52 Minutes
EPYC 7763
July 02 2022
  1 Day, 11 Hours, 9 Minutes
EPYC 7763 2P
July 04 2022
  1 Day, 11 Hours, 44 Minutes
EPYC 7773X
July 01 2022
  1 Day, 7 Hours, 18 Minutes
EPYC 7773X 2P
June 29 2022
  1 Day, 10 Hours, 44 Minutes
Invert Hiding All Results Option
  1 Day, 10 Hours, 20 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 Milan-X Mid-2022 BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionEPYC 7713EPYC 7713 2PEPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PAMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse256GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Mellanox MT27710Ubuntu 22.045.19.0-051900rc4daily20220628-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.31.2.204GCC 11.2.0ext41920x10802 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads)512GBAMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads)256GB2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)512GBAMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads)256GB2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)512GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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 7713: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7713 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7763: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7763 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7773X: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229- EPYC 7773X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229Java Details- OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Details- Python 3.10.4Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7713EPYC 7713 2PEPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PResult OverviewPhoronix Test Suite100%170%239%309%379%RELIONoneDNNPostgreSQL pgbenchACES DGEMMNAS Parallel BenchmarksOSPRay StudioCpuminer-OptXcompact3d Incompact3dLULESHC-RayOpenSSLTachyonGROMACSWRFasmFishJava JMHBlenderm-queensStockfishrays1benchNAMDnginxtoyBrot Fractal GeneratorPrimesievePennantAlgebraic Multi-Grid BenchmarkHigh Performance Conjugate GradientGPAWOSPRayEmbreeIntel Open Image DenoiseLiquid-DSPOpenFOAMTimed Linux Kernel CompilationMariaDBXmrigLeelaChessZeroOpenVKLASKAPTimed Node.js CompilationASTC EncoderTimed LLVM CompilationPOV-RayGraphicsMagickLAMMPS Molecular Dynamics SimulatorKvazaarTimed MPlayer CompilationLuxCoreRenderONNX RuntimeAircrack-ngTimed ImageMagick CompilationSysbenchKTX-Software toktxFacebook RocksDBGoogle Dracox265Apache HTTP ServerNWChemApache CassandraGraph500AOM AV1Zstd CompressionSVT-HEVCFFTETimed Gem5 CompilationTimed Mesa CompilationTimed Godot Game Engine CompilationminiFEClickHousePyHPC Benchmarksx264RodiniaRedisSVT-AV1EtcpakNumpy BenchmarkWebP Image EncodeWebP2 Image Encodelibavif avifenc

AMD EPYC Milan-X Mid-2022 Benchmarkspgbench: 1000 - 250 - Read Write - Average Latencypgbench: 1000 - 250 - Read Writepgbench: 1000 - 500 - Read Write - Average Latencypgbench: 1000 - 500 - Read Writepgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writebrl-cad: VGR Performance Metricnpb: SP.Caskap: tConvolve OpenMP - Griddingrelion: Basic - CPUopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Execution Timecpuminer-opt: Skeincoinaskap: tConvolve MPI - Griddingaskap: tConvolve OpenMP - Degriddingaskap: tConvolve MPI - Degriddingonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUnpb: BT.Cnpb: LU.Copenfoam: drivaerFastback, Large Mesh Size - Execution Timecpuminer-opt: Quad SHA-256, Pyriteonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUaskap: Hogbom Clean OpenMPembree: Pathtracer - Crownembree: Pathtracer ISPC - Crownospray-studio: 1 - 4K - 32 - Path Tracermt-dgemm: Sustained Floating-Point Rateospray-studio: 3 - 4K - 32 - Path Tracerospray-studio: 2 - 4K - 32 - Path Tracercpuminer-opt: LBC, LBRY Creditsopenssl: SHA256cpuminer-opt: Triple SHA-256, Onecoinincompact3d: X3D-benchmarking input.i3dwrf: conus 2.5kmincompact3d: input.i3d 129 Cells Per Directionospray-studio: 3 - 4K - 16 - Path Tracerospray-studio: 1 - 4K - 16 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Tracercpuminer-opt: Blake-2 Sospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 3 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 32 - Path Tracerospray-studio: 3 - 1080p - 1 - Path Tracerospray-studio: 2 - 4K - 16 - Path Tracerrocksdb: Rand Readospray-studio: 1 - 1080p - 16 - Path Tracerospray-studio: 1 - 4K - 1 - Path Tracerospray-studio: 2 - 1080p - 16 - Path Tracerlulesh: ospray-studio: 1 - 1080p - 1 - Path Tracertoybrot: TBBospray-studio: 2 - 1080p - 32 - Path Tracerastcenc: Exhaustivepennant: sedovbigincompact3d: input.i3d 193 Cells Per Directionblender: Classroom - CPU-Onlyospray-studio: 2 - 1080p - 1 - Path Tracercpuminer-opt: Magiospray-studio: 2 - 4K - 1 - Path Tracerc-ray: Total Time - 4K, 16 Rays Per Pixeltachyon: Total Timeblender: Pabellon Barcelona - CPU-Onlygromacs: MPI CPU - water_GMX50_bareliquid-dsp: 256 - 256 - 57openssl: RSA4096npb: MG.Casmfish: 1024 Hash Memory, 26 Depthjava-jmh: Throughputblender: BMW27 - CPU-Onlyopenssl: RSA4096blender: Barbershop - CPU-Onlynpb: EP.Cm-queens: Time To Solvecpuminer-opt: x25xospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timenpb: EP.Dblender: Fishy Cat - CPU-Onlynpb: FT.Ctoybrot: C++ Threadsospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: particle_volume/ao/real_timesysbench: CPUospray: particle_volume/scivis/real_timerays1bench: Large Scenetoybrot: C++ Tasksliquid-dsp: 128 - 256 - 57npb: CG.Cnginx: 500toybrot: OpenMPnamd: ATPase Simulation - 327,506 Atomsnginx: 1000xmrig: Monero - 1Mcpuminer-opt: Garlicoinnginx: 200toktx: UASTC 4 + Zstd Compression 19primesieve: 1e12 Prime Number Generationamg: hpcg: build-linux-kernel: allmodconfigrodinia: OpenMP LavaMDgpaw: Carbon Nanotubenpb: IS.Dcpuminer-opt: Deepcoinrocksdb: Read While Writingoidn: RT.ldr_alb_nrm.3840x2160oidn: RT.hdr_alb_nrm.3840x2160pgbench: 1000 - 250 - Read Only - Average Latencypgbench: 1000 - 250 - Read Onlyoidn: RTLightmap.hdr.4096x4096pgbench: 100 - 250 - Read Onlypgbench: 100 - 250 - Read Only - Average Latencysvt-hevc: 1 - Bosphorus 4Kpennant: leblancbigluxcorerender: Orange Juice - CPUonnx: ArcFace ResNet-100 - CPU - Standardpgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlygraphics-magick: Sharpenkvazaar: Bosphorus 4K - Mediumbuild-llvm: Ninjaluxcorerender: DLSC - CPUmysqlslap: 256npb: SP.Blczero: Eigenembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objcompress-zstd: 19, Long Mode - Compression Speedmysqlslap: 512openvkl: vklBenchmark ISPCgraphics-magick: Enhancedbuild-nodejs: Time To Compileaskap: tConvolve MT - Degriddinglczero: BLASembree: Pathtracer - Asian Dragonrodinia: OpenMP Streamclustergraph500: 26build-linux-kernel: defconfigkvazaar: Bosphorus 4K - Very Fastpovray: Trace Timeembree: Pathtracer - Asian Dragon Objrocksdb: Read Rand Write Randopenfoam: drivaerFastback, Large Mesh Size - Mesh Timecpuminer-opt: Ringcoingraph500: 26lammps: 20k Atomsonnx: bertsquad-12 - CPU - Standardtoktx: UASTC 3 + Zstd Compression 19apache: 1000sysbench: RAM / Memorysvt-hevc: 10 - Bosphorus 4Kopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timebuild-mplayer: Time To Compilexmrig: Wownero - 1Mcompress-zstd: 19 - Compression Speedopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeaircrack-ng: draco: Church Facadegraphics-magick: HWB Color Spacerocksdb: Update Randaom-av1: Speed 10 Realtime - Bosphorus 4Kluxcorerender: Danish Mood - CPUgraphics-magick: Swirlliquid-dsp: 64 - 256 - 57aom-av1: Speed 9 Realtime - Bosphorus 4Kospray: particle_volume/pathtracer/real_timebuild-imagemagick: Time To Compilebuild-llvm: Unix Makefilesaom-av1: Speed 8 Realtime - Bosphorus 4Kx265: Bosphorus 4Kapache: 500apache: 200luxcorerender: LuxCore Benchmark - CPUcassandra: Writesnwchem: C240 Buckyballopenfoam: motorBike - Execution Timedraco: Lionaom-av1: Speed 4 Two-Pass - Bosphorus 4Ktoktx: Zstd Compression 19ffte: N=256, 3D Complex FFT Routinerodinia: OpenMP CFD Solverbuild-gem5: Time To Compilepyhpc: CPU - Numpy - 4194304 - Equation of Statewebp2: Defaulttoktx: UASTC 3build-godot: Time To Compilebuild-mesa: Time To Compilesvt-hevc: 7 - Bosphorus 4Kaom-av1: Speed 6 Two-Pass - Bosphorus 4Kaskap: tConvolve MT - Griddingclickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cachegraph500: 26rodinia: OpenMP Leukocyteminife: Smallkvazaar: Bosphorus 4K - Ultra Fastgraph500: 26astcenc: Thoroughsvt-av1: Preset 12 - Bosphorus 4Kclickhouse: 100M Rows Web Analytics Dataset, Second Rungraphics-magick: Noise-Gaussiansvt-av1: Preset 10 - Bosphorus 4Kcpuminer-opt: Myriad-Groestlclickhouse: 100M Rows Web Analytics Dataset, Third Runopenfoam: motorBike - Mesh Timex264: Bosphorus 4Kredis: GETcompress-zstd: 19 - Decompression Speedavifenc: 6avifenc: 10, Losslesstoktx: Zstd Compression 9svt-av1: Preset 8 - Bosphorus 4Kavifenc: 6, Losslessetcpak: Multi-Threaded - ETC2numpy: webp: Quality 100, Lossless, Highest Compressionwebp: Quality 100, Losslesscompress-zstd: 19, Long Mode - Decompression Speedpyhpc: CPU - Numpy - 4194304 - Isoneutral Mixingwebp2: Quality 95, Compression Effort 7webp2: Quality 100, Lossless Compressionwebp2: Quality 75, Compression Effort 7svt-av1: Preset 4 - Bosphorus 4Kwebp2: Quality 100, Compression Effort 5avifenc: 2avifenc: 0aom-av1: Speed 0 Two-Pass - Bosphorus 4Konnx: super-resolution-10 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: GPT-2 - CPU - Standardredis: SETstockfish: Total Timeaom-av1: Speed 6 Realtime - Bosphorus 4Kgraphics-magick: Resizingluxcorerender: Rainbow Colors and Prism - CPUrodinia: OpenMP HotSpot3DEPYC 7713EPYC 7713 2PEPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2P3.509712518.801568138.053620953.3207529868150452058.019937.18561.975633.77633.5339010022174.88169.2220000.42999.95128297.66136359.2314946.2940128712.3277518.65451.942547.81148499221.0050309978186031126163680386503671362893605.98059116958.8775.1233403347027396802371432275942924118611997973540193262425889995424561010818916.69161976952013513.026411.2799422.006844882.386292049.04248612.34331.9879103.505.0922771166667825669.557354.4013686038072633510998.49632.0312604.4319.274420.6212.2111405.1112.22297.759834779.3940.9460834.0177507.4413615.6496252553.6615.5151279.018054270650000024393.43175415.1382850.45429174541.4328435.91573.17173651.8767.2224.867101353733319.0990272.15146.50072.3952693.324364792504431.401.400.2519953520.6914436360.1739.915.99366212.4215140.339147604050717.74158.8228.2864991426.44356756.873750.750547.3645156928149.1687740.95382263.07715.70831895000029.37636.7210.91256.28603768708887.294544.0925343800026.11157710.423111356.549992.72222.20140.2311.39237332.985.6139.66147923.000751178236535363.866.191873257710000064.13184.65312.617218.59948.2926.70117325.66130660.376.742498602471.461.4456827.4919.791210909.564200306.939176.1870.9782.6244.44943.65420.596137.2513.665121.08383.6162326100041.55321886.255.476452250005.7964186.715386.03542149.48314773393.7937.9370.372359686.403462.03.8905.4382.76561.3627.2246780.236470.0835.46317.2423483.12.059248.775574.212117.1193.5403.55440.58976.8400.21523918042888362008746.5315299940426.39127419.6386.83620.1481255746.3111079932.5181538313.500185953290018114648.265121.44291.339288.69289.82124740343435.16079.4239732.67246.83234205.46260816.477079.8998328029.9442314.31989.624583.04404444332.52953852661455552552101350015522532965190300.3941358627.743.17436776264962222713357684299816496652112054162277952090762055601381574536652.6003504002115227.17335.61817011.138306944.693604084.2714246.35816.510357.728.07653565666671636450.5100462.15249406613146380752899.7817.8025007.0180.878437.336.3892677.3421.386913.36659241.6323.39118216.35422912.731027.5528500974.7727.2564532.354401507853333345687.9188217.1345360.2631289128.5850967.92164087854.7838.6522.640192863266737.0517159.92227.15643.8294655.9872933157571642.242.240.3796615491.1022179640.11315.073.40831918.509710.228219425276128.12104.68712.19411141369.39408467.071659.561936.54252151292104.67212090.0454368.77197.81740656800021.47853.847.83461.08262955644774.013252.8231001000032.2675309.81287425.017561.33196.85126.38.92741507.680.2125.74149434.375748364729350652.087.652105318056666754.28183.16511.197180.83239.8822.0294386.68115214.118.482225782218.271.2457166.5019.916227841.767325646.043156.0421.0082.5703.87941.38118.174144.3912.455848.95391.8967204100045.22523189.857.726937220005.2250174.981411.43563143.32513720407.5539.6668.462468418.083423.54.0715.7192.79063.4647.5566731.708466.6635.69317.2073475.02.068246.367572.082116.1503.5613.54641.72376.5290.21542325232380371977552.4727634664025.6315117.1793.5313.365743108.447591957.533663783.0938083472301551893.199720.45558.552631.51631.7244687023413.38068.3622174.83005.57133627.81143759.0414902.346009711.83128523.57563.043058.09307619524.0542968947277130142653779275697901354657606.86651616576.8215.236623164138834911209863321447257710473176636493535829463545588012167891019362.69254767651785311.533810.3089121.700223572.975532183.42219710.90928.324591.295.6643083666667871716.957289.5715716696774069090884.49328.5113270.4281.104865.7311.9451496.1113.89209.012875263.0636.4561978.1768548.6119017.8202252787.0017.6078299.807190301710000024539.57170624.4673820.38610169469.4831363.71612.59169477.8661.6184.504101601433319.0976236.22642.37369.0942672.725007796752921.641.640.21111838670.8116710330.15011.115.93894013.9615720.302165389257818.43142.4169.5264791176.21371866.060358.320947.36461741027137.1897750.92408671.27635.66029955200026.97638.669.97562.82184232627847.984520.3623546500029.43773410.548117090.009989.44236.96133.1210.69242183.684.9132.76175014.224769778036035363.897.212017279790000065.29184.27612.387206.69347.8326.77108134.82145445.987.762538472344.764.3758527.2720.597247881.142939786.633168.9221.0042.6874.40641.73719.890151.8813.845119.54366.1967102300042.28521751.359.496995770005.8387187.874387.18555153.83414617392.2339.9670.732275602.303307.03.8015.5802.90963.4477.4266712.299446.7137.26418.1413368.32.121250.322576.596117.4253.5473.55740.95076.5840.21663121746585021925547.4616412519226.06131621.0391.95121.8261151948.2741035833.1711508113.83718116115347.485023.7289.190281.79284.23126904045815.66086.4543898.77384.44257261.31289197.747002.3298916029.6601316.792112.0856101.07143672039.63331443685372432944141558104071932997457298.3057668388.6493.1554967621710183111100769780101357552092863431862458704014246211144472037750.567289346594255.86885.39135811.200327437.312944398.5911635.63414.684947.5410.02660103666671736351.7100347.28295020325148366708469.914.8826548.5151.679241.446.2962821.8625.949116.335610098.9919.45118377.12368815.609932.7869503604.5732.4207552.063896558503333346821.5388197.5440770.2261989107.9356954.22499387512.6935.8602.491193793233337.2041142.12224.11842.3294835.1982923161695262.532.530.3666856911.2425486430.09817.193.54880421.499600.200250643385829.4897.16113.83400143388.54449466.875258.695941.2418244145999.76811057.75468771.16338.62944412700020.54753.007.57658.45962971562733.433223.2133978000036.4555699.96583716.927503.24189.60117.878.68950077.684.5117.23161363.901768064430981553.277.782272320020000054.73184.08511.238177.15740.4822.0596356.22116613.238.042235772131.373.8358536.3820.716237497.723985916.020152.2531.0162.5743.94640.67318.394152.6812.415673.14389.4868060400045.70223560.356.097013170005.3029173.430397.28578145.27213459408.1441.5569.702268476.573194.13.8925.8252.92165.4517.6976628.766446.7237.31118.1283300.32.125247.458574.226116.5863.5433.54841.89077.5850.21460124032087061857510.5831702200923.0714616.7185.9643.051819457.452670976.433777202.8378811073435889936.4920708.8291.126366366.9842833035783.619018.331805.52423.06168289.28251998.6112416.8945399311.5957808.11767.366962.06667562629.4091948787675836137507764249664101437047573.98079415534.3844.683471204092234649206343422711254510332174536413488127707587987172154878522217.30454171261757511.63879.63358716.923784976.415462230.72217211.20229.618495.337.2102970400000886927.960883.1415233532178156370321.98129.4713493.2286.915025.5910.9471548.2213.59538.953055329.6537.6364849.8671218.5201217.5109265124.9417.3646304.617411291203333337967.96174606.5176300.38169173749.5835903.71603.52173501.4560.3874.648105324600019.6814234.16444.42758.0672913.884797399196711.631.620.21011899850.8016748530.14910.935.64605413.4616810.303165360258919.16137.2389.21675136930.60507070.929863.007357.86691741047131.9788306.98518877.86495.66433815500026.67740.1410.27571.22854305549726.694667.6026514600029.7397538.105116446.7510345.82242.04114.5110.46239506.6103.5113.12174912.578580984836867168.237.362161277306666770.25192.26810.866198.50250.6027.76119227.93133507.877.61269401224861.5648957.5717.479231182.725266966.509170.1720.8732.5444.42839.64619.672157.2914.175488.05417.8161565500040.28322670.961.286381280005.8483193.538428.41590158.63914467432.7938.7274.822297790.303293.93.7635.5462.96665.4217.2077076.138471.9737.63118.2523316.72.014238.331549.726112.5583.7043.40440.70176.4910.217013201415123981862390.4715982106530.48157023.3888.56410.5952364124.6602027715.777319429.489263603088652228945.2711786.8148.315169.8170.52133754770367.513593.162354.46807.60373690.15394724.965370.47103707729.7636417.200127.3588115.98763528750.56211741541359442923581534610075403101696265.2049367433.9892.3108581020789175751051572771901297526289153281794255247753944521099453242133.734278366590715.93165.0940689.9588691938.792854517.5111315.74115.397148.8111.07458260333331784848.5123826.94284279174156410828590.7215.5127099.3148.699459.245.7232992.6525.704916.402610096.2119.79127926.74384415.573132.6105528284.4232.2495582.923993555293333350299.7785974.9941100.2255487065.3343888.32479087686.1333.9032.455200191600037.6634139.94825.22637.7565085.9781774173375061.951.940.3557049400.9425856610.09717.533.39373021.8110190.194257122288130.6492.54914.04436152554.57589593.451382.656358.9432249143195.05011138.8592396.35747.47339336500019.98052.207.44982.07472987202611.083318.6831297800037.3875437.52786754.447808.75177.70104.448.49049710.6107.5105.26196064.495583068528051755.858.092435334883333357.04149.1819.858171.30241.3121.9597855.03117068.347.522165471996.471.0949346.6017.469225092.739120285.910151.2680.8942.9503.88438.07717.966152.6012.395535.39394.4859699600043.74724565.654.366254990005.3049174.277421.91601144.77913373421.7740.6472.932402083.073320.73.8945.8672.93765.6967.5336969.932475.5137.64918.1523308.92.019238.324551.029112.1653.7053.51141.68377.1220.21494025929288841849652.5432002455422.1015819.0489.974OpenBenchmarking.org

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713510152025SE +/- 0.135, N = 12SE +/- 0.018, N = 3SE +/- 0.454, N = 12SE +/- 0.028, N = 3SE +/- 0.585, N = 12SE +/- 0.033, N = 310.5953.05121.8263.36520.1483.5091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 329.58, N = 12SE +/- 491.57, N = 3SE +/- 286.40, N = 12SE +/- 609.11, N = 3SE +/- 470.27, N = 12SE +/- 676.46, N = 32364181945115197431012557712511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131122334455SE +/- 0.128, N = 3SE +/- 0.030, N = 3SE +/- 0.103, N = 3SE +/- 0.003, N = 3SE +/- 0.485, N = 3SE +/- 0.049, N = 324.6607.45248.2748.44746.3118.8011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771314K28K42K56K70KSE +/- 104.40, N = 3SE +/- 275.42, N = 3SE +/- 22.09, N = 3SE +/- 23.21, N = 3SE +/- 114.03, N = 3SE +/- 315.89, N = 32027767097103585919510799568131. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713816243240SE +/- 0.468, N = 12SE +/- 0.013, N = 3SE +/- 0.332, N = 6SE +/- 0.041, N = 3SE +/- 0.343, N = 5SE +/- 0.061, N = 315.7776.43333.1717.53332.5188.0531. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771317K34K51K68K85KSE +/- 769.35, N = 12SE +/- 158.53, N = 3SE +/- 148.90, N = 6SE +/- 359.40, N = 3SE +/- 161.60, N = 5SE +/- 467.64, N = 33194277720150816637815383620951. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.080, N = 8SE +/- 0.016, N = 3SE +/- 0.203, N = 12SE +/- 0.011, N = 3SE +/- 0.243, N = 12SE +/- 0.003, N = 39.4892.83713.8373.09313.5003.3201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 223.37, N = 8SE +/- 488.29, N = 3SE +/- 299.24, N = 12SE +/- 283.31, N = 3SE +/- 387.83, N = 12SE +/- 67.61, N = 32636088110181168083418595752981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 7773X 2PEPYC 7773XEPYC 7763EPYC 7713 2PEPYC 7713700K1400K2100K2800K3500K308865273435872301532900186815041. (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 -ldl -lm

VGR Performance Metric

EPYC 7763 2P: The test run did not produce a result.

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350K100K150K200K250KSE +/- 897.94, N = 6SE +/- 124.38, N = 3SE +/- 394.38, N = 4SE +/- 45.51, N = 3SE +/- 379.18, N = 4SE +/- 15.05, N = 3228945.2789936.49115347.4851893.19114648.2652058.011. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

ASKAP

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

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134K8K12K16K20KSE +/- 128.89, N = 5SE +/- 155.07, N = 15SE +/- 0.00, N = 4SE +/- 86.27, N = 5SE +/- 53.17, N = 15SE +/- 75.85, N = 511786.8020708.805023.709720.455121.449937.181. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

RELION

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713120240360480600SE +/- 1.22, N = 12SE +/- 3.94, N = 3SE +/- 2.92, N = 5SE +/- 4.13, N = 3SE +/- 3.56, N = 4SE +/- 3.97, N = 3148.32291.13289.19558.55291.34561.981. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713140280420560700169.80366.00281.79631.51288.69633.771. (CXX) g++ options: -std=c++14 -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 9Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713140280420560700170.52366.98284.23631.72289.82633.531. (CXX) g++ options: -std=c++14 -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

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 3.18Algorithm: SkeincoinEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713300K600K900K1200K1500KSE +/- 8275.58, N = 3SE +/- 4254.67, N = 3SE +/- 6040.57, N = 3SE +/- 2789.67, N = 3SE +/- 3452.12, N = 3SE +/- 1332.33, N = 31337547428330126904044687012474033901001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771315K30K45K60K75KSE +/- 395.30, N = 3SE +/- 204.47, N = 3SE +/- 594.93, N = 3SE +/- 172.80, N = 3SE +/- 297.50, N = 3SE +/- 78.33, N = 370367.535783.645815.623413.343435.122174.81. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134K8K12K16K20KSE +/- 171.64, N = 5SE +/- 0.00, N = 14SE +/- 35.18, N = 4SE +/- 0.00, N = 5SE +/- 15.04, N = 15SE +/- 61.76, N = 513593.1019018.306086.458068.366079.428169.221. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771313K26K39K52K65KSE +/- 307.17, N = 3SE +/- 0.00, N = 3SE +/- 546.43, N = 3SE +/- 78.33, N = 3SE +/- 125.73, N = 3SE +/- 287.47, N = 362354.431805.543898.722174.839732.620000.41. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771316003200480064008000SE +/- 66.69, N = 15SE +/- 15.92, N = 3SE +/- 68.91, N = 7SE +/- 15.62, N = 3SE +/- 144.42, N = 15SE +/- 38.63, N = 36807.602423.067384.443005.577246.832999.95MIN: 5996.67MIN: 2337.77MIN: 6840.55MIN: 2904.33MIN: 5303.71MIN: 2866.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771380K160K240K320K400KSE +/- 885.81, N = 5SE +/- 783.65, N = 3SE +/- 548.53, N = 4SE +/- 149.37, N = 3SE +/- 146.54, N = 4SE +/- 209.12, N = 3373690.15168289.28257261.31133627.81234205.46128297.661. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771380K160K240K320K400KSE +/- 2665.84, N = 7SE +/- 1617.25, N = 5SE +/- 808.03, N = 6SE +/- 560.46, N = 4SE +/- 2033.01, N = 5SE +/- 320.45, N = 4394724.96251998.61289197.74143759.04260816.47136359.231. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Large Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133K6K9K12K15K5370.4712416.897002.3214902.307079.8914946.291. (CXX) g++ options: -std=c++14 -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

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 3.18Algorithm: Quad SHA-256, PyriteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713200K400K600K800K1000KSE +/- 13218.24, N = 3SE +/- 36.67, N = 3SE +/- 8037.57, N = 3SE +/- 1200.48, N = 3SE +/- 10283.00, N = 3SE +/- 1627.64, N = 310370774539939891604600979832804012871. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.05, N = 4SE +/- 0.17, N = 15SE +/- 0.24, N = 9SE +/- 0.30, N = 12SE +/- 0.17, N = 4SE +/- 0.16, N = 1229.7611.6029.6611.8329.9412.33MIN: 23.56MIN: 9.23MIN: 22.17MIN: 8.64MIN: 23.7MIN: 10.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

ASKAP

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

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132004006008001000SE +/- 3.71, N = 4SE +/- 3.12, N = 4SE +/- 2.99, N = 4SE +/- 1.58, N = 4SE +/- 3.26, N = 4SE +/- 3.40, N = 15417.20808.12316.79523.58314.32518.651. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150SE +/- 0.25, N = 7SE +/- 0.10, N = 5SE +/- 0.15, N = 7SE +/- 0.06, N = 5SE +/- 0.10, N = 6SE +/- 0.08, N = 4127.3667.37112.0963.0489.6251.94MIN: 114.52 / MAX: 139.8MIN: 65.57 / MAX: 71.96MIN: 99.81 / MAX: 123.02MIN: 61.9 / MAX: 65.27MIN: 83.4 / MAX: 106.77MIN: 50.95 / MAX: 58.07

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150SE +/- 0.17, N = 7SE +/- 0.06, N = 5SE +/- 0.17, N = 6SE +/- 0.10, N = 5SE +/- 0.04, N = 6SE +/- 0.05, N = 4115.9962.07101.0758.0983.0447.81MIN: 104.04 / MAX: 128.8MIN: 60.55 / MAX: 65.97MIN: 92.13 / MAX: 114.57MIN: 56.84 / MAX: 59.91MIN: 77.75 / MAX: 98.95MIN: 46.94 / MAX: 52.88

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 78.94, N = 3SE +/- 257.72, N = 3SE +/- 78.40, N = 3SE +/- 112.25, N = 3SE +/- 39.80, N = 3SE +/- 220.90, N = 33528775626367207619544443849921. (CXX) g++ options: -O3 -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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131122334455SE +/- 0.40, N = 15SE +/- 0.26, N = 6SE +/- 0.27, N = 15SE +/- 0.19, N = 5SE +/- 0.29, N = 15SE +/- 0.22, N = 1550.5629.4139.6324.0532.5321.011. (CC) gcc options: -O3 -march=native -fopenmp

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 34.53, N = 3SE +/- 111.57, N = 3SE +/- 87.68, N = 3SE +/- 80.45, N = 3SE +/- 267.67, N = 3SE +/- 402.31, N = 34154187876436858947252661997811. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 175.50, N = 3SE +/- 53.03, N = 3SE +/- 78.49, N = 3SE +/- 253.75, N = 3SE +/- 12.22, N = 3SE +/- 177.54, N = 33594475836372437713045555860311. (CXX) g++ options: -O3 -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 3.18Algorithm: LBC, LBRY CreditsEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771360K120K180K240K300KSE +/- 5037.87, N = 15SE +/- 803.87, N = 3SE +/- 2561.03, N = 8SE +/- 217.89, N = 3SE +/- 1389.11, N = 3SE +/- 386.71, N = 32923581375072944141426532552101261631. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330000M60000M90000M120000M150000MSE +/- 77628222.70, N = 3SE +/- 138355411.89, N = 3SE +/- 9611091.68, N = 3SE +/- 59113673.97, N = 3SE +/- 37395539.46, N = 3SE +/- 97906207.00, N = 31534610075407642496641015581040719377927569790135001552253680386503671. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -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 3.18Algorithm: Triple SHA-256, OnecoinEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713700K1400K2100K2800K3500KSE +/- 21172.95, N = 15SE +/- 8814.76, N = 3SE +/- 15096.14, N = 3SE +/- 13732.35, N = 3SE +/- 40108.85, N = 3SE +/- 11235.78, N = 33101696143704729974571354657296519013628931. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713130260390520650SE +/- 0.88, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 3SE +/- 1.65, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 3265.20573.98298.31606.87300.39605.981. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134K8K12K16K20K7433.9915534.388388.6516576.828627.7416958.881. (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 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Xcompact3d Incompact3d

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

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.17822.35643.53464.71285.891SE +/- 0.02171361, N = 15SE +/- 0.02960455, N = 7SE +/- 0.02563338, N = 9SE +/- 0.03792635, N = 15SE +/- 0.01476225, N = 8SE +/- 0.02266423, N = 72.310858104.683471203.155496765.236623163.174367765.123340331. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771310K20K30K40K50KSE +/- 26.19, N = 3SE +/- 69.29, N = 3SE +/- 60.85, N = 3SE +/- 37.51, N = 3SE +/- 58.15, N = 3SE +/- 85.38, N = 32078940922217104138826496470271. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77138K16K24K32K40KSE +/- 4.06, N = 3SE +/- 45.85, N = 3SE +/- 27.38, N = 3SE +/- 30.45, N = 3SE +/- 42.74, N = 3SE +/- 14.66, N = 31757534649183113491122227396801. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135K10K15K20K25KSE +/- 7.31, N = 3SE +/- 35.14, N = 3SE +/- 12.06, N = 3SE +/- 18.05, N = 3SE +/- 64.66, N = 3SE +/- 14.77, N = 31051520634110072098613357237141. (CXX) g++ options: -O3 -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 3.18Algorithm: Blake-2 SEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.6M3.2M4.8M6.4M8MSE +/- 62791.55, N = 3SE +/- 37457.49, N = 15SE +/- 69651.90, N = 3SE +/- 2092.08, N = 3SE +/- 60037.01, N = 8SE +/- 24658.55, N = 157277190342271169780103321447684299832275941. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77136001200180024003000SE +/- 1.15, N = 3SE +/- 5.04, N = 3SE +/- 1.67, N = 3SE +/- 1.86, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 31297254513572577164929241. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133K6K9K12K15KSE +/- 10.17, N = 3SE +/- 12.25, N = 3SE +/- 4.91, N = 3SE +/- 9.00, N = 3SE +/- 4.48, N = 3SE +/- 14.05, N = 35262103325520104736652118611. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134K8K12K16K20KSE +/- 5.03, N = 3SE +/- 31.65, N = 3SE +/- 17.32, N = 3SE +/- 4.48, N = 3SE +/- 27.02, N = 3SE +/- 17.48, N = 389151745392861766311205199791. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713160320480640800SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 1.76, N = 33286413436494167351. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77139K18K27K36K45KSE +/- 62.00, N = 3SE +/- 29.13, N = 3SE +/- 29.01, N = 3SE +/- 67.58, N = 3SE +/- 47.37, N = 3SE +/- 100.52, N = 31794234881186243535822779401931. (CXX) g++ options: -O3 -ldl

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 7.0.1Test: Random ReadEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713130M260M390M520M650MSE +/- 520325.54, N = 3SE +/- 151537.43, N = 3SE +/- 1040529.95, N = 3SE +/- 306166.02, N = 3SE +/- 337930.11, N = 3SE +/- 241631.76, N = 35524775392770758795870401422946354555209076202624258891. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 1.53, N = 3SE +/- 16.19, N = 3SE +/- 13.22, N = 3SE +/- 2.52, N = 3SE +/- 6.17, N = 3SE +/- 24.46, N = 34452871746218801556099541. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135001000150020002500SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 1.76, N = 3SE +/- 0.67, N = 3SE +/- 1.73, N = 3SE +/- 2.31, N = 31099215411442167138124561. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 8.39, N = 3SE +/- 5.13, N = 3SE +/- 3.06, N = 3SE +/- 4.67, N = 3SE +/- 4.33, N = 3SE +/- 17.62, N = 345328785472089105745101081. (CXX) g++ options: -O3 -ldl

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77139K18K27K36K45KSE +/- 203.54, N = 3SE +/- 29.30, N = 3SE +/- 100.88, N = 3SE +/- 320.42, N = 12SE +/- 114.44, N = 3SE +/- 388.35, N = 1242133.7322217.3037750.5719362.6936652.6018916.691. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713130260390520650SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 1.76, N = 32785412895473506191. (CXX) g++ options: -O3 -ldl

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771316003200480064008000SE +/- 28.15, N = 15SE +/- 53.34, N = 15SE +/- 23.87, N = 13SE +/- 62.20, N = 7SE +/- 20.96, N = 8SE +/- 44.87, N = 63665712634656765400276951. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134K8K12K16K20KSE +/- 11.72, N = 3SE +/- 11.79, N = 3SE +/- 28.10, N = 3SE +/- 6.11, N = 3SE +/- 14.47, N = 3SE +/- 31.88, N = 390711757594251785311522201351. (CXX) g++ options: -O3 -ldl

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.0015, N = 5SE +/- 0.0055, N = 4SE +/- 0.0047, N = 5SE +/- 0.0020, N = 4SE +/- 0.0433, N = 4SE +/- 0.0084, N = 35.931611.63875.868811.53387.173313.02641. (CXX) g++ options: -O3 -flto -pthread

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.023039, N = 7SE +/- 0.048061, N = 5SE +/- 0.043560, N = 9SE +/- 0.092482, N = 7SE +/- 0.012267, N = 6SE +/- 0.019348, N = 45.0940689.6335875.39135810.3089105.61817011.2799401. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

Xcompact3d Incompact3d

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

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713510152025SE +/- 0.05965355, N = 5SE +/- 0.09430792, N = 3SE +/- 0.11975897, N = 4SE +/- 0.22772804, N = 5SE +/- 0.05325803, N = 4SE +/- 0.00439933, N = 39.9588691916.9237849011.2003274021.7002235011.1383069022.006844801. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Classroom - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 338.7976.4137.3172.9744.6982.38

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713140280420560700SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 32855462945533606291. (CXX) g++ options: -O3 -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 3.18Algorithm: MagiEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771310002000300040005000SE +/- 4.06, N = 3SE +/- 2.00, N = 3SE +/- 45.52, N = 3SE +/- 16.66, N = 10SE +/- 32.59, N = 3SE +/- 21.29, N = 34517.512230.724398.592183.424084.272049.041. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135001000150020002500SE +/- 1.20, N = 3SE +/- 2.91, N = 3SE +/- 1.15, N = 3SE +/- 1.53, N = 3SE +/- 0.33, N = 3SE +/- 3.18, N = 31131217211632197142424861. (CXX) g++ options: -O3 -ldl

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.036, N = 7SE +/- 0.023, N = 5SE +/- 0.044, N = 7SE +/- 0.017, N = 5SE +/- 0.036, N = 6SE +/- 0.032, N = 45.74111.2025.63410.9096.35812.3431. (CC) gcc options: -lm -lpthread -O3

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.07, N = 4SE +/- 0.03, N = 3SE +/- 0.10, N = 4SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 315.4029.6214.6828.3216.5131.991. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

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 NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 348.8195.3347.5491.2957.72103.50

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 2022.1Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.008, N = 3SE +/- 0.022, N = 3SE +/- 0.012, N = 3SE +/- 0.010, N = 3SE +/- 0.033, N = 3SE +/- 0.027, N = 311.0747.21010.0265.6648.0765.0921. (CXX) g++ options: -O3

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: 256 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131300M2600M3900M5200M6500MSE +/- 1241414.96, N = 3SE +/- 2542308.66, N = 3SE +/- 2025120.02, N = 3SE +/- 371184.29, N = 3SE +/- 1017076.42, N = 3SE +/- 5956042.68, N = 35826033333297040000060103666673083666667535656666727711666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713400K800K1200K1600K2000KSE +/- 260.75, N = 3SE +/- 187.94, N = 3SE +/- 692.33, N = 3SE +/- 202.12, N = 3SE +/- 1429.05, N = 3SE +/- 96.70, N = 31784848.5886927.91736351.7871716.91636450.5825669.51. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 1172.23, N = 15SE +/- 236.45, N = 9SE +/- 460.53, N = 10SE +/- 164.34, N = 9SE +/- 306.95, N = 10SE +/- 262.68, N = 9123826.9460883.14100347.2857289.57100462.1557354.401. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771360M120M180M240M300MSE +/- 1637427.52, N = 3SE +/- 1583098.25, N = 3SE +/- 2231292.36, N = 3SE +/- 229968.13, N = 3SE +/- 1043008.23, N = 3SE +/- 1705827.81, N = 3284279174152335321295020325157166967249406613136860380

Java JMH

This very basic test profile runs the stock benchmark of the Java JMH benchmark via Maven. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330000M60000M90000M120000M150000M156410828590.7278156370321.98148366708469.9074069090884.49146380752899.7872633510998.50

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 NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: BMW27 - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.03, N = 4SE +/- 0.04, N = 3SE +/- 0.04, N = 4SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 315.5129.4714.8828.5117.8032.03

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77136K12K18K24K30KSE +/- 27.52, N = 3SE +/- 11.72, N = 3SE +/- 1.20, N = 3SE +/- 9.93, N = 3SE +/- 3.35, N = 3SE +/- 8.87, N = 327099.313493.226548.513270.425007.012604.41. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Barbershop - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771370140210280350SE +/- 0.10, N = 3SE +/- 0.74, N = 3SE +/- 0.32, N = 3SE +/- 0.12, N = 3SE +/- 0.34, N = 3SE +/- 0.24, N = 3148.69286.91151.67281.10180.87319.27

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 88.67, N = 15SE +/- 50.08, N = 15SE +/- 81.68, N = 15SE +/- 46.69, N = 15SE +/- 44.97, N = 11SE +/- 49.60, N = 159459.245025.599241.444865.738437.334420.621. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.011, N = 7SE +/- 0.031, N = 5SE +/- 0.018, N = 7SE +/- 0.022, N = 4SE +/- 0.029, N = 6SE +/- 0.017, N = 45.72310.9476.29611.9456.38912.2111. (CXX) g++ options: -fopenmp -O2 -march=native

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 3.18Algorithm: x25xEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77136001200180024003000SE +/- 26.49, N = 3SE +/- 1.16, N = 3SE +/- 23.10, N = 3SE +/- 9.35, N = 3SE +/- 10.58, N = 3SE +/- 3.01, N = 32992.651548.222821.861496.112677.341405.111. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 325.7013.6025.9513.8921.3912.22

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.00699, N = 3SE +/- 0.01748, N = 3SE +/- 0.01299, N = 3SE +/- 0.00648, N = 3SE +/- 0.00121, N = 3SE +/- 0.02357, N = 316.402608.9530516.335609.0128713.366507.75983

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 162.83, N = 15SE +/- 30.95, N = 3SE +/- 172.09, N = 15SE +/- 5.52, N = 3SE +/- 96.34, N = 15SE +/- 34.69, N = 1110096.215329.6510098.995263.069241.634779.391. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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 NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713918273645SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 319.7937.6319.4536.4523.3940.94

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 1051.45, N = 8SE +/- 237.78, N = 6SE +/- 311.02, N = 8SE +/- 119.43, N = 6SE +/- 174.73, N = 8SE +/- 201.17, N = 6127926.7464849.86118377.1261978.17118216.3560834.011. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771317003400510068008500SE +/- 18.57, N = 8SE +/- 8.09, N = 6SE +/- 11.38, N = 9SE +/- 19.16, N = 6SE +/- 15.91, N = 8SE +/- 17.53, N = 63844712136886854422977501. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.01406, N = 3SE +/- 0.00607, N = 3SE +/- 0.00669, N = 3SE +/- 0.01195, N = 3SE +/- 0.00473, N = 3SE +/- 0.00243, N = 315.573108.5201215.609908.6119012.731007.44136

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/ao/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 332.6117.5132.7917.8227.5515.65

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713110K220K330K440K550KSE +/- 548.86, N = 3SE +/- 26.49, N = 3SE +/- 692.48, N = 3SE +/- 25.96, N = 3SE +/- 722.49, N = 3SE +/- 11.36, N = 3528284.42265124.94503604.57252787.00500974.77252553.661. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/scivis/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713816243240SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 332.2517.3632.4217.6127.2615.52

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713130260390520650SE +/- 0.91, N = 9SE +/- 0.40, N = 8SE +/- 1.95, N = 9SE +/- 0.32, N = 8SE +/- 0.79, N = 9SE +/- 0.38, N = 8582.92304.61552.06299.80532.35279.01

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 12.31, N = 8SE +/- 53.52, N = 6SE +/- 21.18, N = 8SE +/- 38.37, N = 6SE +/- 27.61, N = 8SE +/- 28.36, N = 63993741138967190440180541. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131200M2400M3600M4800M6000MSE +/- 9081911.20, N = 3SE +/- 1271918.94, N = 3SE +/- 6133061.59, N = 3SE +/- 1819340.54, N = 3SE +/- 7913982.00, N = 3SE +/- 721110.26, N = 35552933333291203333355850333333017100000507853333327065000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771311K22K33K44K55KSE +/- 246.00, N = 8SE +/- 286.64, N = 8SE +/- 564.97, N = 15SE +/- 181.78, N = 6SE +/- 341.73, N = 8SE +/- 73.44, N = 650299.7737967.9646821.5324539.5745687.9124393.431. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771340K80K120K160K200KSE +/- 120.41, N = 3SE +/- 178.28, N = 3SE +/- 105.28, N = 3SE +/- 168.64, N = 3SE +/- 72.06, N = 3SE +/- 504.81, N = 385974.99174606.5188197.54170624.4688217.13175415.131. (CC) gcc options: -lcrypt -lz -O3 -march=native

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 13.29, N = 8SE +/- 28.73, N = 6SE +/- 27.11, N = 8SE +/- 17.54, N = 6SE +/- 6.53, N = 8SE +/- 8.92, N = 64110763040777382453682851. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.10220.20440.30660.40880.511SE +/- 0.00014, N = 3SE +/- 0.00018, N = 3SE +/- 0.00041, N = 4SE +/- 0.00429, N = 3SE +/- 0.00189, N = 3SE +/- 0.00038, N = 30.225540.381690.226190.386100.263120.45429

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771340K80K120K160K200KSE +/- 131.31, N = 3SE +/- 47.00, N = 3SE +/- 167.16, N = 3SE +/- 265.95, N = 3SE +/- 191.86, N = 3SE +/- 619.32, N = 387065.33173749.5889107.93169469.4889128.58174541.431. (CC) gcc options: -lcrypt -lz -O3 -march=native

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771312K24K36K48K60KSE +/- 194.70, N = 3SE +/- 30.70, N = 3SE +/- 51.52, N = 3SE +/- 24.15, N = 3SE +/- 176.90, N = 3SE +/- 41.15, N = 343888.335903.756954.231363.750967.928435.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

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 3.18Algorithm: GarlicoinEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135K10K15K20K25KSE +/- 65.06, N = 3SE +/- 10.68, N = 3SE +/- 193.25, N = 3SE +/- 17.20, N = 3SE +/- 30.55, N = 3SE +/- 13.59, N = 324790.001603.5224993.001612.5921640.001573.171. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771340K80K120K160K200KSE +/- 126.91, N = 3SE +/- 275.30, N = 3SE +/- 410.31, N = 3SE +/- 224.07, N = 3SE +/- 277.34, N = 3SE +/- 148.64, N = 387686.13173501.4587512.69169477.8687854.78173651.871. (CC) gcc options: -lcrypt -lz -O3 -march=native

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131530456075SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 333.9060.3935.8661.6238.6567.22

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 7.71e12 Prime Number GenerationEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.09512.19023.28534.38045.4755SE +/- 0.005, N = 10SE +/- 0.004, N = 8SE +/- 0.008, N = 10SE +/- 0.009, N = 8SE +/- 0.005, N = 10SE +/- 0.009, N = 72.4554.6482.4914.5042.6404.8671. (CXX) g++ options: -O3

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713400M800M1200M1600M2000MSE +/- 948996.49, N = 3SE +/- 200642.30, N = 3SE +/- 2223411.97, N = 3SE +/- 829670.28, N = 3SE +/- 1558680.78, N = 3SE +/- 1036538.68, N = 32001916000105324600019379323331016014333192863266710135373331. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713918273645SE +/- 0.46, N = 4SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 337.6619.6837.2019.1037.0519.101. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

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 or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: allmodconfigEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771360120180240300SE +/- 0.50, N = 3SE +/- 0.44, N = 3SE +/- 0.52, N = 3SE +/- 0.45, N = 3SE +/- 0.57, N = 3SE +/- 0.53, N = 3139.95234.16142.12236.23159.92272.15

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131122334455SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.23, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 325.2344.4324.1242.3727.1646.501. (CXX) g++ options: -O2 -lOpenCL

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon NanotubeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131632486480SE +/- 0.15, N = 3SE +/- 0.32, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3SE +/- 0.25, N = 3SE +/- 0.16, N = 337.7658.0742.3369.0943.8372.401. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -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: IS.DEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771311002200330044005500SE +/- 50.11, N = 15SE +/- 23.58, N = 4SE +/- 66.80, N = 15SE +/- 5.68, N = 4SE +/- 47.55, N = 5SE +/- 22.36, N = 45085.972913.884835.192672.724655.982693.321. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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 3.18Algorithm: DeepcoinEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320K40K60K80K100KSE +/- 922.21, N = 15SE +/- 69.36, N = 3SE +/- 1007.51, N = 3SE +/- 268.22, N = 3SE +/- 239.19, N = 3SE +/- 27.28, N = 38177447973829235007772933436471. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

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 7.0.1Test: Read While WritingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134M8M12M16M20MSE +/- 238031.79, N = 15SE +/- 57459.78, N = 3SE +/- 165639.96, N = 15SE +/- 115576.19, N = 4SE +/- 169845.23, N = 15SE +/- 32710.67, N = 31733750699196711616952696752921575716492504431. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.56931.13861.70792.27722.8465SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 31.951.632.531.642.241.40

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.56931.13861.70792.27722.8465SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 31.941.622.531.642.241.40

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.08530.17060.25590.34120.4265SE +/- 0.004, N = 12SE +/- 0.001, N = 3SE +/- 0.006, N = 12SE +/- 0.001, N = 3SE +/- 0.005, N = 12SE +/- 0.001, N = 30.3550.2100.3660.2110.3790.2511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713300K600K900K1200K1500KSE +/- 7420.45, N = 12SE +/- 2502.46, N = 3SE +/- 11859.16, N = 12SE +/- 2600.41, N = 3SE +/- 9287.91, N = 12SE +/- 3282.72, N = 3704940118998568569111838676615499953521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.2790.5580.8371.1161.395SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.940.801.240.811.100.69

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713600K1200K1800K2400K3000KSE +/- 30252.52, N = 4SE +/- 10683.27, N = 3SE +/- 23226.01, N = 3SE +/- 13149.92, N = 3SE +/- 23505.49, N = 5SE +/- 13206.12, N = 32585661167485325486431671033221796414436361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.03890.07780.11670.15560.1945SE +/- 0.001, N = 4SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 5SE +/- 0.002, N = 30.0970.1490.0980.1500.1130.1731. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 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 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 317.5310.9317.1911.1115.079.911. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.34862.69724.04585.39446.743SE +/- 0.058068, N = 15SE +/- 0.044579, N = 15SE +/- 0.108323, N = 15SE +/- 0.078155, N = 13SE +/- 0.042691, N = 15SE +/- 0.059358, N = 63.3937305.6460543.5488045.9389403.4083195.9936621. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

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 2.6Scene: Orange Juice - Acceleration: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713510152025SE +/- 0.24, N = 15SE +/- 0.16, N = 3SE +/- 0.30, N = 15SE +/- 0.08, N = 3SE +/- 0.17, N = 15SE +/- 0.01, N = 321.8113.4621.4913.9618.5012.42MIN: 18.56 / MAX: 28.77MIN: 11.7 / MAX: 15.61MIN: 18.15 / MAX: 29.1MIN: 12.05 / MAX: 16.02MIN: 15.56 / MAX: 23.99MIN: 10.74 / MAX: 14.11

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713400800120016002000SE +/- 17.04, N = 12SE +/- 4.97, N = 3SE +/- 23.14, N = 12SE +/- 22.96, N = 12SE +/- 10.77, N = 3SE +/- 5.67, N = 310191681960157297115141. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.07630.15260.22890.30520.3815SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1940.3030.2000.3020.2280.3391. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713600K1200K1800K2400K3000KSE +/- 8094.03, N = 3SE +/- 7129.48, N = 3SE +/- 13266.33, N = 3SE +/- 5674.85, N = 3SE +/- 10356.45, N = 3SE +/- 4044.18, N = 32571222165360225064331653892219425214760401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132004006008001000SE +/- 1.45, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 1.20, N = 3SE +/- 2.33, N = 38815898585787615071. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.03, N = 330.6419.1629.4818.4328.1217.741. (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 stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134080120160200SE +/- 0.84, N = 3SE +/- 0.08, N = 3SE +/- 0.33, N = 3SE +/- 0.20, N = 3SE +/- 0.43, N = 3SE +/- 0.34, N = 392.55137.2497.16142.42104.69158.82

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 2.6Scene: DLSC - Acceleration: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 314.049.2113.839.5212.198.28MIN: 13.1 / MAX: 17.6MIN: 8.85 / MAX: 9.82MIN: 12.89 / MAX: 18.67MIN: 9.26 / MAX: 10.15MIN: 11.59 / MAX: 15.36MIN: 8.12 / MAX: 8.93

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 256EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713150300450600750SE +/- 5.01, N = 4SE +/- 0.30, N = 3SE +/- 3.41, N = 9SE +/- 0.37, N = 3SE +/- 5.03, N = 9SE +/- 1.70, N = 34366754006474116491. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 1860.50, N = 15SE +/- 992.33, N = 9SE +/- 1211.64, N = 15SE +/- 610.05, N = 8SE +/- 1358.60, N = 15SE +/- 548.98, N = 8152554.57136930.60143388.5491176.21141369.3991426.441. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771313002600390052006500SE +/- 52.39, N = 3SE +/- 24.02, N = 3SE +/- 13.45, N = 3SE +/- 35.12, N = 3SE +/- 8.50, N = 3SE +/- 36.99, N = 95895507044943718408435671. (CXX) g++ options: -flto -pthread

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.82, N = 15SE +/- 0.06, N = 5SE +/- 0.47, N = 12SE +/- 0.05, N = 5SE +/- 0.55, N = 15SE +/- 0.12, N = 493.4570.9366.8866.0667.0756.87MIN: 83.86 / MAX: 101.24MIN: 69.44 / MAX: 73.45MIN: 60.21 / MAX: 73.97MIN: 64.7 / MAX: 67.9MIN: 60.66 / MAX: 73.28MIN: 55.5 / MAX: 58.92

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.52, N = 3SE +/- 0.05, N = 3SE +/- 0.41, N = 15SE +/- 0.02, N = 3SE +/- 0.67, N = 3SE +/- 0.04, N = 382.6663.0158.7058.3259.5650.75MIN: 76.95 / MAX: 87.29MIN: 61.66 / MAX: 64.62MIN: 51.55 / MAX: 64.78MIN: 57.26 / MAX: 60.15MIN: 55.01 / MAX: 64.86MIN: 49.77 / MAX: 52.29

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131326395265SE +/- 0.43, N = 3SE +/- 0.20, N = 3SE +/- 0.52, N = 3SE +/- 0.32, N = 3SE +/- 0.52, N = 15SE +/- 0.37, N = 358.957.841.247.336.547.31. (CC) gcc options: -O3 -pthread -lz -llzma

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 512EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713140280420560700SE +/- 1.31, N = 3SE +/- 0.39, N = 3SE +/- 0.72, N = 3SE +/- 0.87, N = 3SE +/- 1.22, N = 3SE +/- 0.60, N = 34326694186464256451. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

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 1.0Benchmark: vklBenchmark ISPCEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350100150200250SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3249174244174215156MIN: 24 / MAX: 4546MIN: 19 / MAX: 4370MIN: 21 / MAX: 3993MIN: 17 / MAX: 4178MIN: 20 / MAX: 3936MIN: 15 / MAX: 3678

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330060090012001500SE +/- 1.86, N = 3SE +/- 0.88, N = 3SE +/- 15.63, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 3SE +/- 1.00, N = 3143110471459102712929281. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 17.3Time To CompileEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150SE +/- 0.31, N = 3SE +/- 1.33, N = 3SE +/- 0.97, N = 3SE +/- 0.44, N = 3SE +/- 0.35, N = 3SE +/- 0.74, N = 395.05131.9899.77137.19104.67149.17

ASKAP

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

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133K6K9K12K15KSE +/- 291.26, N = 9SE +/- 1.79, N = 3SE +/- 501.02, N = 9SE +/- 4.43, N = 3SE +/- 45.08, N = 3SE +/- 7.34, N = 311138.808306.9811057.757750.9212090.007740.951. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771313002600390052006500SE +/- 61.47, N = 3SE +/- 57.25, N = 4SE +/- 9.49, N = 3SE +/- 53.16, N = 3SE +/- 25.46, N = 3SE +/- 32.70, N = 35923518846874086454338221. (CXX) g++ options: -flto -pthread

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.81, N = 15SE +/- 0.44, N = 5SE +/- 0.79, N = 5SE +/- 0.15, N = 5SE +/- 0.52, N = 5SE +/- 0.19, N = 596.3677.8671.1671.2868.7763.08MIN: 88.29 / MAX: 104.54MIN: 75.45 / MAX: 79.73MIN: 64.35 / MAX: 75.9MIN: 69.42 / MAX: 73.08MIN: 64.52 / MAX: 75.43MIN: 61.44 / MAX: 65.76

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 StreamclusterEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.118, N = 15SE +/- 0.038, N = 7SE +/- 0.572, N = 15SE +/- 0.023, N = 7SE +/- 0.114, N = 15SE +/- 0.026, N = 77.4735.6648.6295.6607.8175.7081. (CXX) g++ options: -O2 -lOpenCL

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713100M200M300M400M500M3933650003381550004441270002995520004065680003189500001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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 or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: defconfigEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.17, N = 9SE +/- 0.28, N = 5SE +/- 0.16, N = 9SE +/- 0.26, N = 6SE +/- 0.18, N = 9SE +/- 0.29, N = 519.9826.6820.5526.9821.4829.38

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131224364860SE +/- 0.53, N = 4SE +/- 0.06, N = 4SE +/- 0.44, N = 5SE +/- 0.04, N = 4SE +/- 0.36, N = 5SE +/- 0.06, N = 452.2040.1453.0038.6653.8436.721. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.043, N = 5SE +/- 0.077, N = 4SE +/- 0.061, N = 5SE +/- 0.015, N = 4SE +/- 0.068, N = 5SE +/- 0.036, N = 47.44910.2757.5769.9757.83410.9121. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.94, N = 4SE +/- 0.06, N = 3SE +/- 0.56, N = 6SE +/- 0.08, N = 3SE +/- 0.44, N = 15SE +/- 0.06, N = 382.0771.2358.4662.8261.0856.29MIN: 74.39 / MAX: 90.19MIN: 69.67 / MAX: 73.01MIN: 54.59 / MAX: 65.62MIN: 61.49 / MAX: 64.53MIN: 54.26 / MAX: 67.56MIN: 55.12 / MAX: 58.32

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 7.0.1Test: Read Random Write RandomEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713900K1800K2700K3600K4500KSE +/- 5452.38, N = 3SE +/- 20018.04, N = 3SE +/- 7325.87, N = 3SE +/- 14439.36, N = 3SE +/- 4886.18, N = 3SE +/- 9608.02, N = 32987202430554929715624232627295564437687081. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Large Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132004006008001000611.08726.69733.43847.98774.01887.291. (CXX) g++ options: -std=c++14 -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

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 3.18Algorithm: RingcoinEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771310002000300040005000SE +/- 23.95, N = 3SE +/- 3.41, N = 3SE +/- 35.30, N = 3SE +/- 19.52, N = 3SE +/- 16.11, N = 3SE +/- 13.75, N = 33318.684667.603223.214520.363252.824544.091. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771370M140M210M280M350M3129780002651460003397800002354650003100100002534380001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713918273645SE +/- 0.40, N = 3SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 337.3929.7436.4629.4432.2726.111. (CXX) g++ options: -O3 -lm

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713160320480640800SE +/- 5.60, N = 5SE +/- 0.76, N = 3SE +/- 4.26, N = 3SE +/- 10.59, N = 3SE +/- 5.67, N = 3SE +/- 3.28, N = 35437535697345305771. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.035, N = 6SE +/- 0.008, N = 6SE +/- 0.047, N = 5SE +/- 0.018, N = 5SE +/- 0.052, N = 5SE +/- 0.016, N = 57.5278.1059.96510.5489.81210.423

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 484.05, N = 3SE +/- 321.37, N = 3SE +/- 327.80, N = 3SE +/- 1193.36, N = 6SE +/- 303.87, N = 3SE +/- 78.03, N = 386754.44116446.7583716.92117090.0087425.01111356.541. (CC) gcc options: -shared -fPIC -O2

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / MemoryEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132K4K6K8K10KSE +/- 62.77, N = 4SE +/- 10.51, N = 5SE +/- 60.31, N = 15SE +/- 16.29, N = 5SE +/- 67.39, N = 15SE +/- 10.33, N = 57808.7510345.827503.249989.447561.339992.721. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350100150200250SE +/- 2.92, N = 15SE +/- 0.57, N = 9SE +/- 1.04, N = 7SE +/- 0.57, N = 9SE +/- 2.09, N = 15SE +/- 0.55, N = 8177.70242.04189.60236.96196.85222.201. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150104.44114.51117.87133.12126.30140.231. (CXX) g++ options: -std=c++14 -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

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.011, N = 5SE +/- 0.024, N = 5SE +/- 0.031, N = 5SE +/- 0.038, N = 5SE +/- 0.039, N = 5SE +/- 0.023, N = 48.49010.4628.68910.6928.92711.392

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771311K22K33K44K55KSE +/- 231.73, N = 3SE +/- 58.89, N = 3SE +/- 17.80, N = 3SE +/- 52.76, N = 3SE +/- 109.61, N = 3SE +/- 15.27, N = 349710.639506.650077.642183.641507.637332.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.28, N = 3SE +/- 1.17, N = 3SE +/- 0.77, N = 3SE +/- 1.05, N = 3SE +/- 1.52, N = 12SE +/- 0.61, N = 3107.5103.584.584.980.285.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150105.26113.12117.23132.76125.74139.661. (CXX) g++ options: -std=c++14 -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

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771340K80K120K160K200KSE +/- 829.37, N = 3SE +/- 951.80, N = 3SE +/- 2573.95, N = 15SE +/- 824.65, N = 3SE +/- 651.38, N = 3SE +/- 379.80, N = 3196064.50174912.58161363.90175014.22149434.38147923.001. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771316003200480064008000SE +/- 10.77, N = 6SE +/- 7.53, N = 6SE +/- 22.05, N = 5SE +/- 14.23, N = 5SE +/- 25.32, N = 5SE +/- 41.42, N = 55830580976807697748375111. (CXX) g++ options: -O3

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77132004006008001000SE +/- 1.53, N = 3SE +/- 0.88, N = 3SE +/- 7.62, N = 3SE +/- 1.53, N = 3SE +/- 1.76, N = 3SE +/- 1.76, N = 36858486447806477821. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 7.0.1Test: Update RandomEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771380K160K240K320K400KSE +/- 2263.57, N = 15SE +/- 2059.34, N = 3SE +/- 2387.17, N = 3SE +/- 2768.25, N = 3SE +/- 2555.21, N = 8SE +/- 1592.99, N = 32805173686713098153603532935063653531. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131530456075SE +/- 0.66, N = 15SE +/- 0.49, N = 12SE +/- 1.06, N = 12SE +/- 0.43, N = 13SE +/- 0.94, N = 12SE +/- 0.36, N = 555.8568.2353.2763.8952.0863.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 2.6Scene: Danish Mood - Acceleration: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.15, N = 15SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 38.097.367.787.217.656.19MIN: 2.98 / MAX: 10.76MIN: 3 / MAX: 8.65MIN: 2.92 / MAX: 9.45MIN: 2.93 / MAX: 8.42MIN: 2.99 / MAX: 9.38MIN: 2.49 / MAX: 7.24

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: SwirlEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135001000150020002500SE +/- 19.04, N = 3SE +/- 11.85, N = 3SE +/- 14.85, N = 3SE +/- 5.55, N = 3SE +/- 4.58, N = 3SE +/- 1.76, N = 32435216122722017210518731. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713700M1400M2100M2800M3500MSE +/- 4642317.43, N = 3SE +/- 2887521.04, N = 3SE +/- 1819340.54, N = 3SE +/- 3134219.73, N = 3SE +/- 4978732.55, N = 3SE +/- 1305118.13, N = 33348833333277306666732002000002797900000318056666725771000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131632486480SE +/- 0.82, N = 15SE +/- 0.48, N = 5SE +/- 0.57, N = 15SE +/- 0.44, N = 5SE +/- 0.87, N = 15SE +/- 0.57, N = 757.0470.2554.7365.2954.2864.131. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/pathtracer/real_timeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134080120160200SE +/- 6.07, N = 9SE +/- 0.69, N = 3SE +/- 0.73, N = 3SE +/- 0.33, N = 3SE +/- 0.71, N = 3SE +/- 0.24, N = 3149.18192.27184.09184.28183.17184.65

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133691215SE +/- 0.046, N = 5SE +/- 0.043, N = 5SE +/- 0.037, N = 5SE +/- 0.034, N = 4SE +/- 0.039, N = 5SE +/- 0.011, N = 49.85810.86611.23812.38711.19712.617

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350100150200250SE +/- 0.65, N = 3SE +/- 0.51, N = 3SE +/- 0.66, N = 3SE +/- 1.08, N = 3SE +/- 0.20, N = 3SE +/- 0.36, N = 3171.30198.50177.16206.69180.83218.60

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131122334455SE +/- 0.37, N = 4SE +/- 0.40, N = 15SE +/- 0.47, N = 4SE +/- 0.59, N = 4SE +/- 0.38, N = 15SE +/- 0.18, N = 441.3150.6040.4847.8339.8848.291. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.17, N = 15SE +/- 0.05, N = 3SE +/- 0.28, N = 15SE +/- 0.07, N = 3SE +/- 0.27, N = 15SE +/- 0.05, N = 321.9527.7622.0526.7722.0226.701. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 769.49, N = 3SE +/- 1223.82, N = 5SE +/- 427.71, N = 3SE +/- 723.59, N = 3SE +/- 551.28, N = 3SE +/- 1526.43, N = 397855.03119227.9396356.22108134.8294386.68117325.661. (CC) gcc options: -shared -fPIC -O2

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330K60K90K120K150KSE +/- 1253.21, N = 3SE +/- 459.18, N = 3SE +/- 615.39, N = 3SE +/- 680.67, N = 3SE +/- 998.53, N = 7SE +/- 381.46, N = 3117068.34133507.87116613.23145445.98115214.11130660.371. (CC) gcc options: -shared -fPIC -O2

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 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.10, N = 15SE +/- 0.04, N = 3SE +/- 0.18, N = 12SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 37.527.618.047.768.486.74MIN: 2.55 / MAX: 10.2MIN: 2.95 / MAX: 8.96MIN: 2.62 / MAX: 11.05MIN: 3 / MAX: 9.1MIN: 2.97 / MAX: 10.37MIN: 2.55 / MAX: 8.02

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771360K120K180K240K300KSE +/- 2805.95, N = 3SE +/- 1619.13, N = 3SE +/- 928.22, N = 3SE +/- 1187.25, N = 3SE +/- 1654.10, N = 3SE +/- 878.03, N = 3216547269401223577253847222578249860

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350010001500200025001996.42248.02131.32344.72218.22471.41. (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 -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: motorBike - Execution TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713163248648071.0961.5673.8364.3771.2461.441. (CXX) g++ options: -std=c++14 -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

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771313002600390052006500SE +/- 3.39, N = 7SE +/- 7.08, N = 7SE +/- 12.54, N = 6SE +/- 6.06, N = 6SE +/- 12.32, N = 6SE +/- 13.15, N = 64934489558535852571656821. (CXX) g++ options: -O3

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 6SE +/- 0.10, N = 36.607.576.387.276.507.491. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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: Zstd Compression 19EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 317.4717.4820.7220.6019.9219.79

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350K100K150K200K250KSE +/- 2779.65, N = 15SE +/- 2168.67, N = 15SE +/- 1730.29, N = 10SE +/- 929.64, N = 11SE +/- 1794.54, N = 10SE +/- 1181.20, N = 10225092.74231182.73237497.72247881.14227841.77210909.561. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.010, N = 7SE +/- 0.009, N = 6SE +/- 0.025, N = 7SE +/- 0.017, N = 6SE +/- 0.020, N = 7SE +/- 0.058, N = 65.9106.5096.0206.6336.0436.9391. (CXX) g++ options: -O2 -lOpenCL

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To CompileEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134080120160200SE +/- 1.68, N = 3SE +/- 1.30, N = 3SE +/- 1.19, N = 3SE +/- 1.33, N = 10SE +/- 1.86, N = 3SE +/- 2.08, N = 3151.27170.17152.25168.92156.04176.19

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.22860.45720.68580.91441.143SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.008, N = 3SE +/- 0.005, N = 30.8940.8731.0161.0041.0080.978

WebP2 Image Encode

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.66381.32761.99142.65523.319SE +/- 0.101, N = 15SE +/- 0.029, N = 15SE +/- 0.027, N = 15SE +/- 0.012, N = 10SE +/- 0.030, N = 15SE +/- 0.023, N = 152.9502.5442.5742.6872.5702.6241. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.0012.0023.0034.0045.005SE +/- 0.019, N = 8SE +/- 0.004, N = 8SE +/- 0.026, N = 8SE +/- 0.003, N = 8SE +/- 0.023, N = 8SE +/- 0.001, N = 83.8844.4283.9464.4063.8794.449

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131020304050SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3SE +/- 0.29, N = 3SE +/- 0.13, N = 338.0839.6540.6741.7441.3843.65

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 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 317.9719.6718.3919.8918.1720.60

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 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 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150SE +/- 0.90, N = 5SE +/- 0.12, N = 7SE +/- 0.93, N = 6SE +/- 0.22, N = 7SE +/- 0.50, N = 6SE +/- 0.25, N = 7152.60157.29152.68151.88144.39137.251. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.15, N = 15SE +/- 0.14, N = 6SE +/- 0.16, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 312.3914.1712.4113.8412.4513.661. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

ASKAP

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

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771313002600390052006500SE +/- 44.86, N = 9SE +/- 2.22, N = 3SE +/- 87.58, N = 9SE +/- 3.20, N = 3SE +/- 6.82, N = 3SE +/- 3.20, N = 35535.395488.055673.145119.545848.955121.081. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, First Run / Cold CacheEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771390180270360450SE +/- 6.54, N = 13SE +/- 5.65, N = 13SE +/- 5.49, N = 3SE +/- 5.07, N = 12SE +/- 3.20, N = 3SE +/- 3.43, N = 3394.48417.81389.48366.19391.89383.61MIN: 49.46 / MAX: 20000MIN: 42.31 / MAX: 20000MIN: 44.54 / MAX: 20000MIN: 37.01 / MAX: 20000MIN: 44.68 / MAX: 15000MIN: 37.59 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713150M300M450M600M750M5969960006156550006806040006710230006720410006232610001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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 LeukocyteEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131020304050SE +/- 0.16, N = 3SE +/- 0.55, N = 3SE +/- 0.49, N = 3SE +/- 0.22, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 343.7540.2845.7042.2945.2341.551. (CXX) g++ options: -O2 -lOpenCL

miniFE

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

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77135K10K15K20K25KSE +/- 385.10, N = 12SE +/- 41.69, N = 4SE +/- 322.64, N = 15SE +/- 110.33, N = 3SE +/- 274.51, N = 15SE +/- 10.03, N = 424565.622670.923560.321751.323189.821886.21. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131428425670SE +/- 0.32, N = 5SE +/- 0.66, N = 15SE +/- 0.54, N = 5SE +/- 0.82, N = 15SE +/- 0.43, N = 5SE +/- 0.84, N = 1554.3661.2856.0959.4957.7255.471. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713150M300M450M600M750M6254990006381280007013170006995770006937220006452250001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.31592.63183.94775.26366.5795SE +/- 0.0083, N = 7SE +/- 0.0027, N = 7SE +/- 0.0049, N = 7SE +/- 0.0015, N = 7SE +/- 0.0060, N = 7SE +/- 0.0014, N = 75.30495.84835.30295.83875.22505.79641. (CXX) g++ options: -O3 -flto -pthread

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 1.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134080120160200SE +/- 2.17, N = 15SE +/- 0.60, N = 8SE +/- 1.58, N = 15SE +/- 0.67, N = 8SE +/- 1.28, N = 15SE +/- 0.69, N = 8174.28193.54173.43187.87174.98186.721. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Second RunEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771390180270360450SE +/- 2.37, N = 13SE +/- 2.18, N = 13SE +/- 10.96, N = 3SE +/- 2.74, N = 12SE +/- 2.38, N = 3SE +/- 3.24, N = 3421.91428.41397.28387.18411.43386.03MIN: 74.91 / MAX: 20000MIN: 47.36 / MAX: 20000MIN: 69.2 / MAX: 8571.43MIN: 42.08 / MAX: 20000MIN: 68.18 / MAX: 15000MIN: 41.58 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713130260390520650SE +/- 4.84, N = 3SE +/- 1.33, N = 3SE +/- 1.20, N = 3SE +/- 2.08, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 36015905785555635421. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 1.0Encoder Mode: Preset 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77134080120160200SE +/- 1.16, N = 6SE +/- 0.61, N = 7SE +/- 0.82, N = 6SE +/- 0.98, N = 7SE +/- 1.00, N = 7SE +/- 0.49, N = 7144.78158.64145.27153.83143.33149.481. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 3.18Algorithm: Myriad-GroestlEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133K6K9K12K15KSE +/- 179.38, N = 3SE +/- 53.33, N = 3SE +/- 115.73, N = 15SE +/- 12.02, N = 3SE +/- 20.82, N = 3SE +/- 150.59, N = 31337314467134591461713720147731. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Third RunEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771390180270360450SE +/- 2.94, N = 13SE +/- 2.22, N = 13SE +/- 5.58, N = 3SE +/- 1.18, N = 12SE +/- 6.38, N = 3SE +/- 4.48, N = 3421.77432.79408.14392.23407.55393.79MIN: 72.82 / MAX: 20000MIN: 46.66 / MAX: 20000MIN: 67.57 / MAX: 15000MIN: 41.78 / MAX: 20000MIN: 64.86 / MAX: 20000MIN: 41.35 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: motorBike - Mesh TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771391827364540.6438.7241.5539.9639.6637.931. (CXX) g++ options: -std=c++14 -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

x264

This is a multi-threaded test of the x264 video encoder run on the CPU with a choice of 1080p or 4K video input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.54, N = 6SE +/- 1.20, N = 15SE +/- 0.60, N = 15SE +/- 0.97, N = 15SE +/- 0.40, N = 5SE +/- 0.92, N = 1572.9374.8269.7070.7368.4670.371. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713500K1000K1500K2000K2500KSE +/- 21745.09, N = 15SE +/- 23060.14, N = 5SE +/- 43059.17, N = 15SE +/- 24226.71, N = 15SE +/- 53051.04, N = 15SE +/- 25175.34, N = 152402083.072297790.302268476.572275602.302468418.082359686.401. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77137001400210028003500SE +/- 40.59, N = 3SE +/- 41.59, N = 3SE +/- 78.99, N = 3SE +/- 43.02, N = 3SE +/- 15.02, N = 12SE +/- 32.08, N = 33320.73293.93194.13307.03423.53462.01. (CC) gcc options: -O3 -pthread -lz -llzma

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.9161.8322.7483.6644.58SE +/- 0.030, N = 8SE +/- 0.026, N = 13SE +/- 0.018, N = 8SE +/- 0.021, N = 8SE +/- 0.030, N = 8SE +/- 0.017, N = 83.8943.7633.8923.8014.0713.8901. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131.32012.64023.96035.28046.6005SE +/- 0.022, N = 7SE +/- 0.006, N = 7SE +/- 0.005, N = 7SE +/- 0.024, N = 7SE +/- 0.023, N = 7SE +/- 0.009, N = 75.8675.5465.8255.5805.7195.4381. (CXX) g++ options: -O3 -fPIC -lm

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: Zstd Compression 9EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.66741.33482.00222.66963.337SE +/- 0.001, N = 9SE +/- 0.008, N = 9SE +/- 0.005, N = 9SE +/- 0.005, N = 9SE +/- 0.004, N = 10SE +/- 0.003, N = 102.9372.9662.9212.9092.7902.765

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 1.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131530456075SE +/- 0.64, N = 4SE +/- 0.30, N = 5SE +/- 0.49, N = 11SE +/- 0.44, N = 5SE +/- 0.77, N = 4SE +/- 0.40, N = 565.7065.4265.4563.4563.4661.361. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713246810SE +/- 0.018, N = 6SE +/- 0.026, N = 6SE +/- 0.033, N = 6SE +/- 0.027, N = 6SE +/- 0.050, N = 6SE +/- 0.044, N = 67.5337.2077.6977.4267.5567.2241. (CXX) g++ options: -O3 -fPIC -lm

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771315003000450060007500SE +/- 29.06, N = 8SE +/- 36.09, N = 9SE +/- 27.97, N = 8SE +/- 12.15, N = 8SE +/- 31.87, N = 8SE +/- 20.60, N = 96969.937076.146628.776712.306731.716780.241. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713100200300400500SE +/- 1.12, N = 3SE +/- 1.20, N = 3SE +/- 0.53, N = 3SE +/- 2.07, N = 3SE +/- 1.41, N = 3SE +/- 1.79, N = 3475.51471.97446.72446.71466.66470.08

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713918273645SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 337.6537.6337.3137.2635.6935.461. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771348121620SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 318.1518.2518.1318.1417.2117.241. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77137001400210028003500SE +/- 0.84, N = 3SE +/- 11.85, N = 3SE +/- 12.54, N = 3SE +/- 35.92, N = 3SE +/- 15.26, N = 15SE +/- 32.53, N = 33308.93316.73300.33368.33475.03483.11. (CC) gcc options: -O3 -pthread -lz -llzma

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.47810.95621.43431.91242.3905SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.004, N = 3SE +/- 0.006, N = 32.0192.0142.1252.1212.0682.059

WebP2 Image Encode

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771350100150200250SE +/- 0.40, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 1.17, N = 3SE +/- 0.54, N = 3SE +/- 0.44, N = 3238.32238.33247.46250.32246.37248.781. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Lossless CompressionEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713120240360480600SE +/- 0.30, N = 3SE +/- 1.66, N = 3SE +/- 0.79, N = 3SE +/- 0.76, N = 3SE +/- 0.26, N = 3SE +/- 0.61, N = 3551.03549.73574.23576.60572.08574.211. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713306090120150SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 3112.17112.56116.59117.43116.15117.121. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

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 1.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.83361.66722.50083.33444.168SE +/- 0.015, N = 3SE +/- 0.014, N = 3SE +/- 0.009, N = 3SE +/- 0.014, N = 3SE +/- 0.007, N = 3SE +/- 0.005, N = 33.7053.7043.5433.5473.5613.5401. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

WebP2 Image Encode

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Compression Effort 5EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.80031.60062.40093.20124.0015SE +/- 0.015, N = 9SE +/- 0.002, N = 9SE +/- 0.023, N = 8SE +/- 0.002, N = 9SE +/- 0.024, N = 14SE +/- 0.004, N = 93.5113.4043.5483.5573.5463.5541. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77131020304050SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 341.6840.7041.8940.9541.7240.591. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0EPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 0.27, N = 3SE +/- 0.10, N = 3SE +/- 0.27, N = 3SE +/- 0.06, N = 3SE +/- 0.24, N = 3SE +/- 0.32, N = 377.1276.4977.5976.5876.5376.841. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77130.04730.09460.14190.18920.2365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 30.210.210.210.210.210.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771315003000450060007500SE +/- 252.84, N = 9SE +/- 0.88, N = 3SE +/- 46.74, N = 3SE +/- 0.83, N = 3SE +/- 270.61, N = 12SE +/- 308.79, N = 124940701346016631542352391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771360120180240300SE +/- 5.67, N = 12SE +/- 9.87, N = 9SE +/- 9.14, N = 9SE +/- 14.66, N = 12SE +/- 5.99, N = 12SE +/- 1.89, N = 32592012402172521801. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713100200300400500SE +/- 11.96, N = 9SE +/- 3.61, N = 3SE +/- 7.08, N = 12SE +/- 14.33, N = 12SE +/- 9.44, N = 9SE +/- 1.69, N = 32924153204653234281. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 77133K6K9K12K15KSE +/- 597.46, N = 12SE +/- 19.68, N = 3SE +/- 276.08, N = 12SE +/- 22.27, N = 3SE +/- 232.52, N = 12SE +/- 170.57, N = 1288841239887068502803788361. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713400K800K1200K1600K2000KSE +/- 33749.09, N = 13SE +/- 12740.72, N = 4SE +/- 37226.45, N = 12SE +/- 38668.55, N = 12SE +/- 21365.65, N = 15SE +/- 35055.76, N = 151849652.541862390.471857510.581925547.461977552.472008746.531. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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 15Total TimeEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771370M140M210M280M350MSE +/- 5231696.32, N = 15SE +/- 697166.64, N = 3SE +/- 5420401.92, N = 13SE +/- 2920642.93, N = 15SE +/- 5015802.16, N = 15SE +/- 3217246.33, N = 123200245541598210653170220091641251922763466401529994041. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713714212835SE +/- 0.17, N = 3SE +/- 0.33, N = 3SE +/- 0.59, N = 15SE +/- 0.68, N = 15SE +/- 0.31, N = 4SE +/- 0.66, N = 1522.1030.4823.0726.0625.6326.391. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771330060090012001500SE +/- 9.91, N = 15SE +/- 24.62, N = 15SE +/- 4.66, N = 15SE +/- 18.66, N = 3SE +/- 4.90, N = 15SE +/- 12.04, N = 71581570146131615112741. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 7713612182430SE +/- 0.32, N = 15SE +/- 0.70, N = 15SE +/- 0.10, N = 15SE +/- 0.53, N = 15SE +/- 0.22, N = 15SE +/- 0.56, N = 1519.0423.3816.7121.0317.1719.63MIN: 16.18 / MAX: 20.84MIN: 18.62 / MAX: 26.34MIN: 15.15 / MAX: 18.2MIN: 17.27 / MAX: 23.14MIN: 15.07 / MAX: 18.67MIN: 16.39 / MAX: 23.86

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 HotSpot3DEPYC 7773X 2PEPYC 7773XEPYC 7763 2PEPYC 7763EPYC 7713 2PEPYC 771320406080100SE +/- 1.61, N = 15SE +/- 1.58, N = 12SE +/- 0.72, N = 3SE +/- 1.65, N = 15SE +/- 1.16, N = 3SE +/- 1.51, N = 1589.9788.5685.9691.9593.5386.841. (CXX) g++ options: -O2 -lOpenCL

238 Results Shown

PostgreSQL pgbench:
  1000 - 250 - Read Write - Average Latency
  1000 - 250 - Read Write
  1000 - 500 - Read Write - Average Latency
  1000 - 500 - Read Write
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
BRL-CAD
NAS Parallel Benchmarks
ASKAP
RELION
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Execution Time
Cpuminer-Opt
ASKAP:
  tConvolve MPI - Gridding
  tConvolve OpenMP - Degridding
  tConvolve MPI - Degridding
oneDNN
NAS Parallel Benchmarks:
  BT.C
  LU.C
OpenFOAM
Cpuminer-Opt
oneDNN
ASKAP
Embree:
  Pathtracer - Crown
  Pathtracer ISPC - Crown
OSPRay Studio
ACES DGEMM
OSPRay Studio:
  3 - 4K - 32 - Path Tracer
  2 - 4K - 32 - Path Tracer
Cpuminer-Opt
OpenSSL
Cpuminer-Opt
Xcompact3d Incompact3d
WRF
Xcompact3d Incompact3d
OSPRay Studio:
  3 - 4K - 16 - Path Tracer
  1 - 4K - 16 - Path Tracer
  3 - 1080p - 32 - Path Tracer
Cpuminer-Opt
OSPRay Studio:
  3 - 4K - 1 - Path Tracer
  3 - 1080p - 16 - Path Tracer
  1 - 1080p - 32 - Path Tracer
  3 - 1080p - 1 - Path Tracer
  2 - 4K - 16 - Path Tracer
Facebook RocksDB
OSPRay Studio:
  1 - 1080p - 16 - Path Tracer
  1 - 4K - 1 - Path Tracer
  2 - 1080p - 16 - Path Tracer
LULESH
OSPRay Studio
toyBrot Fractal Generator
OSPRay Studio
ASTC Encoder
Pennant
Xcompact3d Incompact3d
Blender
OSPRay Studio
Cpuminer-Opt
OSPRay Studio
C-Ray
Tachyon
Blender
GROMACS
Liquid-DSP
OpenSSL
NAS Parallel Benchmarks
asmFish
Java JMH
Blender
OpenSSL
Blender
NAS Parallel Benchmarks
m-queens
Cpuminer-Opt
OSPRay:
  gravity_spheres_volume/dim_512/pathtracer/real_time
  gravity_spheres_volume/dim_512/ao/real_time
NAS Parallel Benchmarks
Blender
NAS Parallel Benchmarks
toyBrot Fractal Generator
OSPRay:
  gravity_spheres_volume/dim_512/scivis/real_time
  particle_volume/ao/real_time
Sysbench
OSPRay
rays1bench
toyBrot Fractal Generator
Liquid-DSP
NAS Parallel Benchmarks
nginx
toyBrot Fractal Generator
NAMD
nginx
Xmrig
Cpuminer-Opt
nginx
KTX-Software toktx
Primesieve
Algebraic Multi-Grid Benchmark
High Performance Conjugate Gradient
Timed Linux Kernel Compilation
Rodinia
GPAW
NAS Parallel Benchmarks
Cpuminer-Opt
Facebook RocksDB
Intel Open Image Denoise:
  RT.ldr_alb_nrm.3840x2160
  RT.hdr_alb_nrm.3840x2160
PostgreSQL pgbench:
  1000 - 250 - Read Only - Average Latency
  1000 - 250 - Read Only
Intel Open Image Denoise
PostgreSQL pgbench:
  100 - 250 - Read Only
  100 - 250 - Read Only - Average Latency
SVT-HEVC
Pennant
LuxCoreRender
ONNX Runtime
PostgreSQL pgbench:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
GraphicsMagick
Kvazaar
Timed LLVM Compilation
LuxCoreRender
MariaDB
NAS Parallel Benchmarks
LeelaChessZero
Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
Zstd Compression
MariaDB
OpenVKL
GraphicsMagick
Timed Node.js Compilation
ASKAP
LeelaChessZero
Embree
Rodinia
Graph500
Timed Linux Kernel Compilation
Kvazaar
POV-Ray
Embree
Facebook RocksDB
OpenFOAM
Cpuminer-Opt
Graph500
LAMMPS Molecular Dynamics Simulator
ONNX Runtime
KTX-Software toktx
Apache HTTP Server
Sysbench
SVT-HEVC
OpenFOAM
Timed MPlayer Compilation
Xmrig
Zstd Compression
OpenFOAM
Aircrack-ng
Google Draco
GraphicsMagick
Facebook RocksDB
AOM AV1
LuxCoreRender
GraphicsMagick
Liquid-DSP
AOM AV1
OSPRay
Timed ImageMagick Compilation
Timed LLVM Compilation
AOM AV1
x265
Apache HTTP Server:
  500
  200
LuxCoreRender
Apache Cassandra
NWChem
OpenFOAM
Google Draco
AOM AV1
KTX-Software toktx
FFTE
Rodinia
Timed Gem5 Compilation
PyHPC Benchmarks
WebP2 Image Encode
KTX-Software toktx
Timed Godot Game Engine Compilation
Timed Mesa Compilation
SVT-HEVC
AOM AV1
ASKAP
ClickHouse
Graph500
Rodinia
miniFE
Kvazaar
Graph500
ASTC Encoder
SVT-AV1
ClickHouse
GraphicsMagick
SVT-AV1
Cpuminer-Opt
ClickHouse
OpenFOAM
x264
Redis
Zstd Compression
libavif avifenc:
  6
  10, Lossless
KTX-Software toktx
SVT-AV1
libavif avifenc
Etcpak
Numpy Benchmark
WebP Image Encode:
  Quality 100, Lossless, Highest Compression
  Quality 100, Lossless
Zstd Compression
PyHPC Benchmarks
WebP2 Image Encode:
  Quality 95, Compression Effort 7
  Quality 100, Lossless Compression
  Quality 75, Compression Effort 7
SVT-AV1
WebP2 Image Encode
libavif avifenc:
  2
  0
AOM AV1
ONNX Runtime:
  super-resolution-10 - CPU - Standard
  fcn-resnet101-11 - CPU - Standard
  yolov4 - CPU - Standard
  GPT-2 - CPU - Standard
Redis
Stockfish
AOM AV1
GraphicsMagick
LuxCoreRender
Rodinia