April 2023 AMD Zen 4 Linux Benchmarks

Benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2303304-PTS-EARLYUPP87
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 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
Web Browsers 1 Tests
Chess Test Suite 3 Tests
Timed Code Compilation 6 Tests
C/C++ Compiler Tests 15 Tests
Compression Tests 2 Tests
CPU Massive 27 Tests
Creator Workloads 23 Tests
Cryptography 2 Tests
Database Test Suite 4 Tests
Encoding 9 Tests
Fortran Tests 3 Tests
Game Development 4 Tests
HPC - High Performance Computing 19 Tests
Imaging 3 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 7 Tests
Molecular Dynamics 7 Tests
MPI Benchmarks 5 Tests
Multi-Core 31 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 9 Tests
Productivity 2 Tests
Programmer / Developer System Benchmarks 10 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 4 Tests
Scientific Computing 10 Tests
Server 9 Tests
Server CPU Tests 19 Tests
Single-Threaded 4 Tests
Video Encoding 8 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

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

Additional Graphs

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Ryzen 5 7600X
March 28 2023
  1 Day, 4 Hours, 15 Minutes
Ryzen 7 7700X
March 26 2023
  23 Hours, 32 Minutes
Ryzen 9 7900X
March 27 2023
  1 Day, 54 Minutes
Ryzen 9 7900X3D
March 25 2023
  1 Day, 51 Minutes
Ryzen 9 7950X
March 24 2023
  21 Hours, 55 Minutes
Ryzen 9 7950X3D
March 29 2023
  1 Day, 3 Hours, 55 Minutes
Invert Hiding All Results Option
  1 Day, 1 Hour, 14 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):


April 2023 AMD Zen 4 Linux BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)AMD Ryzen 9 7900X3D 12-Core @ 4.40GHz (12 Cores / 24 Threads)AMD Ryzen 7 7700X 8-Core @ 4.50GHz (8 Cores / 16 Threads)AMD Ryzen 9 7900X 12-Core @ 4.70GHz (12 Cores / 24 Threads)AMD Ryzen 5 7600X 6-Core @ 4.70GHz (6 Cores / 12 Threads)AMD Ryzen 9 7950X3D 16-Core @ 4.20GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (9927 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 2000GBAMD Radeon RX 7900 XTX (2304/1249MHz)AMD Device ab30ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.2.8-060208-generic (x86_64)GNOME Shell 44.0X Server 1.21.1.7 + Wayland4.6 Mesa 23.1.0-devel (git-de8b14f 2023-03-24 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49)OpenCL 2.1 AMD-APP (3513.0)GCC 12.2.0ext43840x2160ProcessorsMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionApril 2023 AMD Zen 4 Linux Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/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-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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- OpenJDK Runtime Environment (build 17.0.6+10-Ubuntu-1ubuntu2)- Python 3.11.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 7950XRyzen 9 7900X3DRyzen 7 7700XRyzen 9 7900XRyzen 5 7600XRyzen 9 7950X3DLogarithmic Result OverviewPhoronix Test SuiteLULESHACES DGEMMOpenSSLBlenderChaos Group V-RAYStockfishNAMDJohn The RipperCloverLeafStargate Digital Audio WorkstationEmbreeOSPRayOSPRay StudioBRL-CADoneDNN7-Zip Compressionuvg266OpenVKLGROMACSTimed Linux Kernel CompilationTimed Node.js CompilationTimed LLVM CompilationTimed Godot Game Engine Compilationnginxx264Timed FFmpeg CompilationStress-NGPennantBuild2SPECFEM3DRocksDBASKAPGPAWSVT-AV1OpenVINODarktableVVenCx265NCNNOpenFOAMMemcachedOpenCVXcompact3d Incompact3dONNX RuntimeSeleniumClickHouseZstd CompressionVP9 libvpx EncodingGIMPdav1dLeelaChessZeroGoogle DracoCraftyDarmstadt Automotive Parallel Heterogeneous SuiteFFmpegPyBenchsimdjsonPHPBenchWebP Image EncodeNumpy BenchmarkGNU Octave Benchmark

April 2023 AMD Zen 4 Linux Benchmarkslulesh: openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUstress-ng: CPU Cachencnn: CPU - blazefaceospray-studio: 1 - 1080p - 32 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Traceraskap: tConvolve OpenMP - Degriddingospray-studio: 3 - 1080p - 1 - Path Tracerospray-studio: 1 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 1 - Path Tracerospray-studio: 3 - 1080p - 16 - Path Traceropenvino: Weld Porosity Detection FP16-INT8 - CPUstress-ng: Context Switchingmt-dgemm: Sustained Floating-Point Rateopenvino: Age Gender Recognition Retail 0013 FP16 - CPUstress-ng: CPU Stressstress-ng: Vector Mathopenvino: Person Vehicle Bike Detection FP16 - CPUncnn: CPU - shufflenet-v2openssl: SHA256openssl: SHA512stress-ng: Cryptoopenvino: Face Detection FP16-INT8 - CPUopenssl: RSA4096john-the-ripper: bcryptjohn-the-ripper: Blowfishstress-ng: Matrix Mathcompress-7zip: Decompression Ratingrocksdb: Rand Readopenssl: ChaCha20openvino: Weld Porosity Detection FP16 - CPUblender: BMW27 - CPU-Onlyjohn-the-ripper: WPA PSKospray: gravity_spheres_volume/dim_512/pathtracer/real_timeblender: Pabellon Barcelona - CPU-Onlyblender: Fishy Cat - CPU-Onlyjohn-the-ripper: MD5openssl: ChaCha20-Poly1305ospray: gravity_spheres_volume/dim_512/ao/real_timencnn: CPU - regnety_400mv-ray: CPUopenssl: AES-256-GCMospray: gravity_spheres_volume/dim_512/scivis/real_timestargate: 96000 - 1024openssl: AES-128-GCMopenssl: RSA4096ospray: particle_volume/ao/real_timeopenvino: Face Detection FP16 - CPUstockfish: Total Timeembree: Pathtracer ISPC - Crownospray: particle_volume/scivis/real_timenamd: ATPase Simulation - 327,506 Atomsembree: Pathtracer - Crownonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUstargate: 192000 - 1024onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUopenvino: Vehicle Detection FP16 - CPUcloverleaf: Lagrangian-Eulerian Hydrodynamicsonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUstargate: 96000 - 512openvino: Person Detection FP16 - CPUembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objopenvino: Person Detection FP32 - CPUstargate: 192000 - 512build-linux-kernel: allmodconfigbrl-cad: VGR Performance Metriconednn: IP Shapes 3D - bf16bf16bf16 - CPUembree: Pathtracer ISPC - Asian Dragononednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUembree: Pathtracer ISPC - Asian Dragon Objuvg266: Bosphorus 4K - Super Fastaskap: tConvolve OpenMP - Griddingx264: Bosphorus 4Knginx: 200onednn: IP Shapes 1D - bf16bf16bf16 - CPUncnn: CPU-v3-v3 - mobilenet-v3build-llvm: Ninjaopenvkl: vklBenchmark ISPCncnn: CPU - mnasnetuvg266: Bosphorus 4K - Ultra Fastnginx: 100gromacs: MPI CPU - water_GMX50_bareuvg266: Bosphorus 4K - Very Fastnginx: 1000nginx: 500build-nodejs: Time To Compilebuild-godot: Time To Compilestress-ng: Memory Copyingopenfoam: drivaerFastback, Small Mesh Size - Execution Timepennant: leblancbigbuild-llvm: Unix Makefilesopenvino: Machine Translation EN To DE FP16 - CPUbuild-ffmpeg: Time To Compilejohn-the-ripper: HMAC-SHA512opencv: Videobuild-linux-kernel: defconfigspecfem3d: Layered Halfspaceaskap: tConvolve MPI - Degriddingbuild2: Time To Compilecompress-7zip: Compression Ratingx264: Bosphorus 1080pdarktable: Server Rack - CPU-onlyrocksdb: Read While Writingaskap: tConvolve MPI - Griddingpennant: sedovbigncnn: CPU-v2-v2 - mobilenet-v2specfem3d: Mount St. Helensx265: Bosphorus 4Kvvenc: Bosphorus 4K - Fastsvt-av1: Preset 8 - Bosphorus 4Kcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8 - Compression Speedapache: 1000darktable: Boat - CPU-onlyspecfem3d: Water-layered Halfspacencnn: CPU - efficientnet-b0svt-av1: Preset 4 - Bosphorus 4Kspecfem3d: Homogeneous Halfspacegpaw: Carbon Nanotubespecfem3d: Tomographic Modelospray: particle_volume/pathtracer/real_timevvenc: Bosphorus 4K - Fastermemcached: 1:10vvenc: Bosphorus 1080p - Fastmemcached: 1:10apache: 500svt-av1: Preset 12 - Bosphorus 4Kcompress-zstd: 12 - Compression Speedrocksdb: Read Rand Write Randincompact3d: input.i3d 129 Cells Per Directionsvt-av1: Preset 13 - Bosphorus 4Kdarktable: Masskrug - CPU-onlymemcached: 1:100askap: tConvolve MT - Degriddingmemcached: 1:100ncnn: CPU - googlenetopenfoam: drivaerFastback, Small Mesh Size - Mesh Timememcached: 1:5openfoam: drivaerFastback, Medium Mesh Size - Mesh Timedav1d: Summer Nature 4Kaskap: Hogbom Clean OpenMPx265: Bosphorus 1080popenfoam: drivaerFastback, Medium Mesh Size - Execution Timevvenc: Bosphorus 1080p - Fasteropenvino: Person Vehicle Bike Detection FP16 - CPUgimp: resizeincompact3d: input.i3d 193 Cells Per Directionvpxenc: Speed 5 - Bosphorus 4Kaskap: tConvolve MT - Griddingopenvino: Vehicle Detection FP16 - CPUopencv: Image Processingopenvino: Face Detection FP16-INT8 - CPUclickhouse: 100M Rows Hits Dataset, Third Rundarktable: Server Room - CPU-onlyrocksdb: Update Randclickhouse: 100M Rows Hits Dataset, Second Runselenium: PSPDFKit WASM - Firefoxncnn: CPU - vision_transformeropenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUncnn: CPU - squeezenet_ssdvpxenc: Speed 0 - Bosphorus 4Kopenvino: Person Detection FP32 - CPUclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachencnn: CPU - mobilenetselenium: PSPDFKit WASM - Google Chromeopenvino: Machine Translation EN To DE FP16 - CPUgimp: unsharp-maskvpxenc: Speed 0 - Bosphorus 1080pdaphne: OpenMP - Points2Imagecompress-zstd: 19, Long Mode - Compression Speedopenvino: Vehicle Detection FP16-INT8 - CPUapache: 200vpxenc: Speed 5 - Bosphorus 1080papache: 100draco: Church Facadedav1d: Summer Nature 1080plczero: Eigenonnx: GPT-2 - CPU - Standardopencv: Graph APIcompress-zstd: 19 - Compression Speedncnn: CPU - yolov4-tinyncnn: CPU - alexnetncnn: CPU - resnet18ffmpeg: libx265 - Uploadffmpeg: libx265 - Uploadlczero: BLASncnn: CPU - resnet50ffmpeg: libx265 - Platformffmpeg: libx265 - Platformffmpeg: libx265 - Video On Demandffmpeg: libx265 - Video On Demandgimp: auto-levelsopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopencv: Features 2Ddav1d: Chimera 1080psimdjson: PartialTweetsopencv: Stitchingcrafty: Elapsed Timeopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUdraco: Lionselenium: Jetstream 2 - Google Chromeffmpeg: libx265 - Liveffmpeg: libx265 - Liveopencv: Coresimdjson: DistinctUserIDgimp: rotatesimdjson: TopTweetncnn: CPU - vgg16selenium: Kraken - Google Chromepybench: Total For Average Test Timescompress-zstd: 19 - Decompression Speedselenium: Jetstream 2 - Firefoxdav1d: Chimera 1080p 10-bitsimdjson: LargeRandselenium: Kraken - Firefoxdaphne: OpenMP - Euclidean Clustersimdjson: Kostyacompress-zstd: 19, Long Mode - Decompression Speedffmpeg: libx264 - Liveffmpeg: libx264 - Livedaphne: OpenMP - NDT Mappingffmpeg: libx264 - Platformffmpeg: libx264 - Platformffmpeg: libx264 - Video On Demandffmpeg: libx264 - Video On Demandffmpeg: libx264 - Uploadffmpeg: libx264 - Uploadselenium: WASM imageConvolute - Firefoxselenium: Speedometer - Firefoxselenium: WASM collisionDetection - Firefoxselenium: Speedometer - Google Chromewebp: Defaultselenium: WASM collisionDetection - Google Chromephpbench: PHP Benchmark Suitewebp: Quality 100, Highest Compressionnumpy: octave-benchmark: webp: Quality 100compress-zstd: 12 - Decompression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 8, Long Mode - Decompression Speedopencv: DNN - Deep Neural Networkopencv: Object Detectionselenium: WASM imageConvolute - Google Chromeonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: GPT-2 - CPU - Standardncnn: CPU - FastestDetspark: 1000000 - 100Ryzen 9 7950XRyzen 9 7900X3DRyzen 7 7700XRyzen 9 7900XRyzen 5 7600XRyzen 9 7950X3D8539.757726125.901.695262868842.431.5629432351876111.41109714683919175762894.708930648.8811.19090644976.4861633.57146978.581670.003.59368764732171187789624362992.3528.41396563.64694046733130771.711837121505534411379013934171447.0149.381765699.52467158.8163.914662667980140590908.1490711.48326792300180875937.925105.96299526775329651015483.57.9966114.457673931834.27947.945180.7714831.87363.557331855.481133.723.904150577.363771.3746.810.2103365.5586667.6532.702329.07887.543.560690512.2434262881.5615834.95161.4061729.860850.926075.7777.15188361.900.6549453.19328.8884093.2559.81188405.162.60846.30152268.17173022.34273.108169.6517725.73160.4260724.30418353.401136.8321.4992020823332542145.69978.0796953801071069.756183767297.380.155436894911577.534.666583.7031.72299328535.957.80574.792856.4836.72.34078.4303665784.655.71441.772868898137.88534.157523620249.60015.1334124930.5723.8174054196.00217.159254.7347314014.4937051222.2242.6603690970.442838.933693334.628.5622.4850954117576.04189.28477395.58442.500122.992100.711444.9484.7812.24465.936683723.672148.4510.3679864280.96276.802.332989730275.51212877.835.52551.981039.1912.4610.881054.73247.729.23241258.4212.44421.8235141.53877826812.94.3043.7644001509.371768167.14212206523.515.195.027.4037.5167.32189512.8377.1598.1998.2277.1210.0590.6133828991.488.41111007154319050.355.523443347.39625.55197.634160210.058.7279.8925.76346.05102124.5865.981.83482.82315.405.892012.215.87318.241472.06104.2572.66104.0872.7818.88133.7418.1304.8244.739927.92217.9712575385.40945.334.61617.282463.92369.42392.6195281944317.8416.110762.79024.30723232.1542.15659467.03426.478637.7646273.9463.650330.8568731178.4152.619819.398188.237911.513735.980984.469055.272117588.981.371352261408.131.46418514995010186.421559212911330249001951.946210682.938.00644930248.7141808.60102534.491183.173.6425333420457807718285044106.9319.40278454.9324803244192493.9113079710653197897762009177993.1170.031227946.69392225.1990.463076333694232141375.7945510.84234051618671990105.702373.87609918819415800010345.05.6337410.085333642125.53365.623321.0827423.89615.221781254.431559.982.560802802.170791.9930.960.2949633.6840215.6325.837923.31765.522.456949673.5432987621.1578029.56782.0139925.196333.456033.8556.36135184.241.067573.08409.4683293.1939.27134927.902.28331.20129547.31132147.38337.733212.9385447.10139.4750119.30214439.272106.6427.5011493773333116857.68893.04307559910008.0185.971154925230.390.189327310012175.631.146713.5540.31594988328.826.08859.527941.81031.0163211.392.96990.5824682274.364.60446.238722602143.85336.814966208199.15612.3653510381.4319.7293471647.55177117.15189.398299.5269434712.5325611193.0632.9283183961.702927.903179844.538.1726.1739323261982.16196.47774366.43552.493102.711913.590639.9545.0713.31361.353869121.712114.757.5785537308.86303.042.494809930301.88219293.646.04593.741058.9611.669.841079.72268.009.10317556.2412.93719.3334161.85246735114.44.78204878.1839.10185877.5536471269.551772188.84213883925.214.674.076.4132.6877.26188512.3567.31112.54112.7167.2110.6000.6837002861.747.32123364134475110.396.143545322.62828.49177.25430678.979.7679.8124.41380.55202062.8189.722789.571.68507.42173.135.961860.917.28292.311397.77112.1967.52111.7067.8217.60143.4618.1291.5245.437926.34230.9112075005.27924.614.79116.882426.52343.72369.8240811980019.1316.844660.40127.52862138.5852.35730428.14535.633228.0665368.2152.747881.11652895.19957.847717.6404107.42749.604205.314174.378017.063413428.543.152555845633.350.5562682738844098.162213295921850353181491.004388025.245.67951123143.2130478.1173951.14887.851.4518758255480604536179731973.0114.82201878.7238642380866937.51935597682421370980755090745.0697.00910484.86544309.02124.402391667504881706334.172274.65167771188682131234.088523.2894051389037749138056.84.125997.543939872617.66114.107731.4874416.53316.87028942.042062.842.1658271026.63486.2169.440.3879943.1578174.1517.860416.06694.162.071484948.6282385182.3611920.35402.2534617.364828.163385.4743.40109607.621.145811.43585.8592301.5033.93110819.101.54726.5698019.87104108.32476.887296.4754667.35248.8311132.54760605.03782.8036.5521247760001578277.080124.9453499905788.76114.595113954187.730.24828535726787.1146.626681.9253.31056908118.575.08149.125561.1551.0134983.403.533120.7941278642.623.96557.780174901191.06245.624536434166.64210.6523221061.7017.3533210247.22161549.06157.556195.6267544818.5838089168.7363.5233162482.242122.353147488.475.6730.3954193591302.95232.3856343.08423.73391.942506.414837.7604.509.50576.883303328.511784.988.2262606269.69252.602.790837216251.53279992.915.36529.80960.709.3511.61957.75229.197.02312148.2910.22822.3741450.64500524311.64.24202785.7449.75198848.6744881440.051539153.11411177320.512.274.276.0333.5175.35168510.7469.04109.72109.6469.099.0980.59312161011.838.44107407151256590.345.363498366.43727.11186.284139710.138.8749.7525.09344.65042154.7207.586865.981.84464.02281.335.932028.116.10313.661510.77104.9172.20104.7772.3018.86133.8617.7307.4246.040227.91226.1112434455.48964.344.66517.382465.42389.32413.6123662249717.3014.997866.67026.54158152.9242.62505380.86632.390832.5150460.0872.173501.22820813.89258.315818.544270.209914.24806.529101.878553.704819880.371.812982186099.111.3839193468295675.31466196221228234482195.496683204.628.57946234149.6945586.84109496.961273.293.4527774892630895436015047474.8121.44295424.5349843489299161.501374551146529351043931236131093.6565.311322377.18054209.3384.083507667742366231676.1491910.09248521748759006776.007134.22519020413587692711924.16.0463011.015554615526.10946.025331.0066624.30284.817511398.201431.032.803825731.940738.4848.690.2646713.9992466.0225.921823.24605.932.627352649.9603237591.5430129.06141.7989624.765237.154992.6961.51148467.630.9746132.96401.8183283.0643.72147810.432.26834.76133655.23142134.15330.169207.8226023.67172.5132225.05771424.143111.0726.1501630460002624955.49490.74348271410092.185.303156647253.730.187341376511693.236.851463.4442.46865332530.486.69164.759808.9862.8140125.352.76289.2818151174.195.09344.308705280150.83633.707327963209.62713.4853646277.8821.7443566082.94158235.02196.117248.6282052814.6754833202.8682.9423374511.842766.953381093.618.3024.8821053428414.42201.08433368.45439.079112.672170.640843.0874.7112.32667.071820624.072009.508.1281536279.40286.692.502844521281.89281482.765.48543.31992.0111.9110.821004.91255.898.43313853.9912.41021.3235526.67389811312.84.29211000.5243.64156497.1445761382.591744174.82812360523.414.034.737.0835.9770.20190912.3273.54103.01102.8473.6610.0280.634214943.858.21114629145103380.355.463585346.16526.16193.02426609.808.9219.4124.79349.95132175.5203.574839.581.78479.92310.296.051953.116.08314.121462.04105.9271.52105.9971.4718.57135.9917.9304.6245.039527.47220.8812620585.50934.874.81117.582419.62397.82421.9230722076417.3716.578461.11837.07961145.6602.24269448.40025.907039.5055463.8042.292880.9750821038.02663.577916.282593.028710.937775.718394.121786.08478561.503.244934401318.960.5583779995505145.572998400742506478971067.993332864.044.17671516786.8423168.8355522.03631.711.5214019104657452157284323979.5310.84151335.5179351788250108.06704655778464853007348987556.39128.42679353.66513412.55165.781797667378102323433.152504.7212661891488463433.072152.3145911040098541576019.23.114935.632995204013.38913.109741.9709212.53869.04052730.502874.181.5420101445.76404.6571.670.5236912.2514503.1113.756812.44543.131.4888721224.0621789712.6108515.73803.3237913.434521.682942.6333.3381518.681.511191.55743.2301791.6326.3583186.071.19220.4974596.4478427.06599.257373.1463512.67271.0138936.76304763.37063.3845.994944633331676996.342160.1651770855248.85144.64291081144.600.31421576376348.2854.177991.9262.04486304018.854.05938.905523.5543.2117763.774.400147.0423089692.853.20774.133708971223.23459.184326172142.4408.7912439025.7514.1302418021.17137368.84131.317182.3211349019.9036026140.8774.1102388901.551916.922391691.966.4434.2260272762729.11264.53391275.71379.87386.312632.442331.9406.339.55981.502944920.501687.089.8868959368.29230.633.178727188230.062125104.507.18707.511281.599.598.741272.19215.227.28242563.1210.14117.2543360.59426564211.75.47164764.6949.97157972.3645141199.851484151.10911360020.412.814.406.7231.1381.11159611.7264.69117.10117.0064.759.2050.7033758876.168.33111490148305820.355.613526360.05128.91174.70414959.968.8679.6227.23349.15132108.2208.299800.691.83467.82118.195.871941.416.20311.681498.88106.7770.95107.0670.7518.47136.7417.9311.2249.739527.53230.4212166555.39946.664.67717.092451.62359.72396.9125282357017.5415.852363.077310.3456497.73703.11772321.55336.724828.8702678.0461.5508781.30479766.18073.567614.77027109.40519.725576.616301.789097.680323606.791.082501987512.191.61315163715511503.2117815867971186102616.108280952.5411.09286040616.9559420.40138158.811666.233.82340830613871086594540758628.4026.10375876.24391643921123807.351758041424231981308000494471337.3652.161654418.97591168.0467.504172667929108185277.7035312.02313662165818663837.569755.62790425153960099713817.57.5716013.517317448034.07177.550980.8157431.88493.942321707.051215.853.696535623.4831012.4528.770.2296395.2028207.3433.709530.30987.313.355091516.6554035181.0975737.23771.5130631.755146.366888.4671.98179232.780.7222343.29323.8854073.4154.45177681.072.69441.84168262.81175066.40269.139168.8557102.84124.4223516.89291355.890136.1322.0181881003333370246.31876.26587022711010.769.893188382268.520.157428458912698.227.093403.7732.50233998134.447.21870.0181001.31036.7223853.852.49578.3333855114.705.29243.061064944126.80435.011465927228.75314.1933982059.1221.9773938540.03230091.81213.524299.9334298412.5259216214.8402.6683564857.902960.623554398.248.7524.3522523953637.22180.58871402.89547.676112.991849.378642.2364.8012.79658.293711322.092323.167.8981537305.98314.372.347958852312.03286683.995.98590.691082.5111.909.991086.14284.219.27315958.7213.15519.7833484.37486189815.04.68204101.1240.13164236.1536141409.201857185.99913928425.314.834.376.8134.5273.15189412.2970.80106.99106.5871.0810.8350.6735434913.127.59120452145666940.396.113150329.34927.67182.49468209.239.1648.8525.12378.75561981.1198.861831.741.71502.32207.795.551897.016.80300.571424.88110.2268.73109.6669.0818.03140.0518.9294.8260.138227.55229.4712263015.46945.794.71017.242488.22404.22410.0218332003218.8115.543065.61126.46818161.9652.11160475.36224.950940.8059275.9363.624020.9182021109.30662.576616.225682.116912.17755.375834.60OpenBenchmarking.org

LULESH

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

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2K4K6K8K10KSE +/- 26.27, N = 7SE +/- 4.30, N = 8SE +/- 15.25, N = 6SE +/- 4.68, N = 6SE +/- 20.10, N = 7SE +/- 10.98, N = 69097.681786.088553.708017.069055.278539.761. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6K12K18K24K30KSE +/- 15.43, N = 3SE +/- 27.53, N = 3SE +/- 36.67, N = 3SE +/- 7.96, N = 3SE +/- 5.14, N = 3SE +/- 19.36, N = 323606.798561.5019880.3713428.5417588.9826125.901. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.73011.46022.19032.92043.6505SE +/- 0.00121, N = 7SE +/- 0.00353, N = 7SE +/- 0.00252, N = 7SE +/- 0.00306, N = 7SE +/- 0.00054, N = 7SE +/- 0.00812, N = 71.082503.244931.812983.152551.371351.69526MIN: 1.03MIN: 3.17MIN: 1.75MIN: 3.08MIN: 1.35MIN: 1.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: CPU CacheRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.3M2.6M3.9M5.2M6.5MSE +/- 30111.46, N = 15SE +/- 34972.41, N = 3SE +/- 22413.02, N = 3SE +/- 72128.97, N = 3SE +/- 4040.61, N = 3SE +/- 39256.30, N = 151987512.194401318.962186099.115845633.352261408.132868842.431. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.36230.72461.08691.44921.8115SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 7SE +/- 0.01, N = 12SE +/- 0.02, N = 4SE +/- 0.04, N = 31.610.551.380.551.461.56MIN: 1.47 / MAX: 7.74MIN: 0.49 / MAX: 4.7MIN: 1.32 / MAX: 7.12MIN: 0.52 / MAX: 4.68MIN: 1.39 / MAX: 17.44MIN: 1.47 / MAX: 36.411. (CXX) g++ options: -O3 -rdynamic -lgomp -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: 32 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20K40K60K80K100KSE +/- 41.08, N = 3SE +/- 101.69, N = 3SE +/- 51.11, N = 3SE +/- 106.89, N = 3SE +/- 57.81, N = 3SE +/- 22.10, N = 33151683779391936268241851294321. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20K40K60K80K100KSE +/- 320.57, N = 3SE +/- 290.34, N = 3SE +/- 58.24, N = 3SE +/- 64.17, N = 3SE +/- 10.99, N = 3SE +/- 42.44, N = 33715599550468297388449950351871. (CXX) g++ options: -O3 -lm -ldl

ASKAP

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

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2K4K6K8K10KSE +/- 153.85, N = 6SE +/- 165.08, N = 6SE +/- 108.00, N = 6SE +/- 39.27, N = 6SE +/- 54.18, N = 7SE +/- 83.88, N = 511503.205145.575675.304098.1610186.426111.411. (CXX) g++ options: -O3 -fstrict-aliasing -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: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6001200180024003000SE +/- 3.48, N = 3SE +/- 3.79, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 1.20, N = 31178299814662213155910971. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X9K18K27K36K45KSE +/- 13.57, N = 3SE +/- 103.96, N = 3SE +/- 40.70, N = 3SE +/- 25.24, N = 3SE +/- 5.13, N = 3SE +/- 4.18, N = 31586740074196222959221291146831. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 5.84, N = 3SE +/- 1.45, N = 3SE +/- 2.00, N = 3SE +/- 3.18, N = 3SE +/- 2.60, N = 3SE +/- 0.58, N = 397125061228185013309191. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10K20K30K40K50KSE +/- 180.23, N = 3SE +/- 100.36, N = 3SE +/- 14.34, N = 3SE +/- 48.79, N = 3SE +/- 6.03, N = 3SE +/- 10.50, N = 31861047897234483531824900175761. (CXX) g++ options: -O3 -lm -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6001200180024003000SE +/- 1.47, N = 3SE +/- 1.89, N = 3SE +/- 1.22, N = 3SE +/- 1.59, N = 3SE +/- 2.00, N = 3SE +/- 5.17, N = 32616.101067.992195.491491.001951.942894.701. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Context SwitchingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2M4M6M8M10MSE +/- 58598.77, N = 3SE +/- 12124.10, N = 3SE +/- 53501.91, N = 3SE +/- 8621.39, N = 3SE +/- 75039.03, N = 4SE +/- 90303.53, N = 68280952.543332864.046683204.624388025.246210682.938930648.881. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

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 RateRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.114795, N = 15SE +/- 0.035651, N = 12SE +/- 0.063420, N = 3SE +/- 0.070442, N = 3SE +/- 0.014153, N = 3SE +/- 0.123200, N = 311.0928604.1767158.5794625.6795118.00644911.1909061. (CC) gcc options: -O3 -march=native -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10K20K30K40K50KSE +/- 63.20, N = 3SE +/- 200.07, N = 3SE +/- 23.20, N = 3SE +/- 62.88, N = 3SE +/- 6.01, N = 3SE +/- 58.03, N = 340616.9516786.8434149.6923143.2130248.7144976.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: CPU StressRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X13K26K39K52K65KSE +/- 130.71, N = 3SE +/- 243.21, N = 5SE +/- 340.75, N = 3SE +/- 248.37, N = 3SE +/- 143.52, N = 3SE +/- 410.92, N = 1559420.4023168.8345586.8430478.1141808.6061633.571. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Vector MathRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30K60K90K120K150KSE +/- 42.17, N = 3SE +/- 15.42, N = 3SE +/- 5.16, N = 3SE +/- 43.37, N = 3SE +/- 38.31, N = 3SE +/- 1868.35, N = 3138158.8155522.03109496.9673951.14102534.49146978.581. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X400800120016002000SE +/- 0.62, N = 3SE +/- 2.45, N = 3SE +/- 5.25, N = 3SE +/- 1.24, N = 3SE +/- 5.71, N = 3SE +/- 15.62, N = 31666.23631.711273.29887.851183.171670.001. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.85951.7192.57853.4384.2975SE +/- 0.03, N = 14SE +/- 0.01, N = 14SE +/- 0.02, N = 7SE +/- 0.01, N = 11SE +/- 0.01, N = 4SE +/- 0.01, N = 33.821.523.451.453.643.59MIN: 3.6 / MAX: 102.47MIN: 1.47 / MAX: 5.96MIN: 3.34 / MAX: 9.35MIN: 1.39 / MAX: 7.3MIN: 3.56 / MAX: 3.87MIN: 3.39 / MAX: 37.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 3.1Algorithm: SHA256Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X8000M16000M24000M32000M40000MSE +/- 34835211.23, N = 3SE +/- 8147449.84, N = 3SE +/- 9268070.35, N = 3SE +/- 23422908.44, N = 3SE +/- 17850918.80, N = 3SE +/- 14905556.09, N = 33408306138714019104657277748926301875825548025333420457368764732171. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3000M6000M9000M12000M15000MSE +/- 4981029.00, N = 3SE +/- 1516718.41, N = 3SE +/- 2906689.88, N = 3SE +/- 648242.55, N = 3SE +/- 2012680.78, N = 3SE +/- 706456.47, N = 3108659454074521572843895436015060453617978077182850118778962431. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: CryptoRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X13K26K39K52K65KSE +/- 222.65, N = 3SE +/- 68.01, N = 3SE +/- 32.72, N = 3SE +/- 61.93, N = 3SE +/- 359.43, N = 13SE +/- 79.86, N = 358628.4023979.5347474.8131973.0144106.9362992.351. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 326.1010.8421.4414.8219.4028.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 3.1Algorithm: RSA4096Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X80K160K240K320K400KSE +/- 131.45, N = 3SE +/- 73.28, N = 3SE +/- 3000.81, N = 3SE +/- 192.25, N = 3SE +/- 31.72, N = 3SE +/- 115.21, N = 3375876.2151335.5295424.5201878.7278454.9396563.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10K20K30K40K50KSE +/- 50.05, N = 3SE +/- 36.88, N = 3SE +/- 32.42, N = 3SE +/- 57.50, N = 3SE +/- 38.97, N = 3SE +/- 118.42, N = 34391617935349842386432480469401. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10K20K30K40K50KSE +/- 53.53, N = 3SE +/- 34.94, N = 3SE +/- 11.55, N = 3SE +/- 36.09, N = 3SE +/- 73.96, N = 3SE +/- 87.21, N = 34392117882348922380832441467331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Matrix MathRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30K60K90K120K150KSE +/- 182.43, N = 3SE +/- 85.53, N = 3SE +/- 156.30, N = 3SE +/- 89.13, N = 3SE +/- 83.36, N = 3SE +/- 85.06, N = 3123807.3550108.0699161.5066937.5192493.91130771.711. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 398.09, N = 3SE +/- 209.34, N = 3SE +/- 301.73, N = 3SE +/- 56.15, N = 3SE +/- 281.33, N = 3SE +/- 404.67, N = 317580470465137455935591307971837121. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

RocksDB

This is a benchmark of Meta/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 BetterRocksDB 8.0Test: Random ReadRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30M60M90M120M150MSE +/- 71922.56, N = 3SE +/- 386524.38, N = 3SE +/- 145291.54, N = 3SE +/- 518042.81, N = 3SE +/- 77605.89, N = 3SE +/- 393815.64, N = 314242319857784648114652935768242131065319781505534411. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 3.1Algorithm: ChaCha20Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30000M60000M90000M120000M150000MSE +/- 50740995.75, N = 3SE +/- 3351916.44, N = 3SE +/- 32700124.58, N = 3SE +/- 2287404.12, N = 3SE +/- 4098947.09, N = 3SE +/- 33952426.18, N = 31308000494475300734898710439312361370980755090977620091771379013934171. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 0.14, N = 3SE +/- 0.59, N = 3SE +/- 0.69, N = 3SE +/- 0.58, N = 3SE +/- 0.51, N = 3SE +/- 1.47, N = 31337.36556.391093.65745.06993.111447.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: CPU-OnlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 352.16128.4265.3197.0070.0349.38

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 546.53, N = 3SE +/- 68.21, N = 3SE +/- 113.24, N = 3SE +/- 219.54, N = 3SE +/- 90.21, N = 3SE +/- 355.52, N = 316544167935132237910481227941765691. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.01069, N = 3SE +/- 0.00579, N = 3SE +/- 0.00534, N = 3SE +/- 0.00213, N = 3SE +/- 0.00404, N = 3SE +/- 0.00581, N = 38.975913.665137.180544.865446.693929.52467

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: CPU-OnlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X90180270360450SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.23, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 3168.04412.55209.33309.02225.19158.81

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: CPU-OnlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X4080120160200SE +/- 0.06, N = 3SE +/- 0.55, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 367.50165.7884.08124.4090.4663.91

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1000K2000K3000K4000K5000KSE +/- 1452.97, N = 3SE +/- 1201.85, N = 3SE +/- 6333.33, N = 3SE +/- 1666.67, N = 3SE +/- 881.92, N = 3SE +/- 8412.95, N = 34172667179766735076672391667307633346626671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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 3.1Algorithm: ChaCha20-Poly1305Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20000M40000M60000M80000M100000MSE +/- 18286198.46, N = 3SE +/- 1775123.27, N = 3SE +/- 7146104.90, N = 3SE +/- 9313096.26, N = 3SE +/- 44766456.82, N = 3SE +/- 7300302.65, N = 39291081852737810232343742366231675048817063369423214137980140590901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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/ao/real_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00256, N = 3SE +/- 0.01020, N = 3SE +/- 0.02378, N = 3SE +/- 0.01753, N = 3SE +/- 0.01886, N = 3SE +/- 0.04136, N = 37.703533.152506.149194.172275.794558.14907

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.09, N = 15SE +/- 0.03, N = 15SE +/- 0.06, N = 7SE +/- 0.02, N = 12SE +/- 0.06, N = 4SE +/- 0.16, N = 312.024.7210.094.6510.8411.48MIN: 11.13 / MAX: 54.52MIN: 4.47 / MAX: 12.85MIN: 9.75 / MAX: 78.59MIN: 4.43 / MAX: 10.61MIN: 10.58 / MAX: 22.78MIN: 11.02 / MAX: 57.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Chaos Group V-RAY

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

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5.02Mode: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X7K14K21K28K35KSE +/- 47.94, N = 3SE +/- 3.00, N = 3SE +/- 53.72, N = 3SE +/- 43.14, N = 3SE +/- 87.86, N = 3SE +/- 67.51, N = 3313661266124852167772340532679

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 3.1Algorithm: AES-256-GCMRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50000M100000M150000M200000M250000MSE +/- 161187700.98, N = 3SE +/- 34295936.80, N = 3SE +/- 52022105.73, N = 3SE +/- 62514843.80, N = 3SE +/- 91047476.57, N = 3SE +/- 184417335.88, N = 3216581866383891488463431748759006771188682131231618671990102300180875931. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.01462, N = 3SE +/- 0.00203, N = 3SE +/- 0.00117, N = 3SE +/- 0.01549, N = 3SE +/- 0.01960, N = 3SE +/- 0.01094, N = 37.569753.072156.007134.088525.702377.92510

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 1024Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.34172.68344.02515.36686.7085SE +/- 0.018911, N = 3SE +/- 0.002874, N = 3SE +/- 0.007006, N = 3SE +/- 0.004366, N = 3SE +/- 0.022017, N = 3SE +/- 0.033943, N = 35.6279042.3145914.2251903.2894053.8760995.9629951. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

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 3.1Algorithm: AES-128-GCMRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60000M120000M180000M240000M300000MSE +/- 268142967.38, N = 3SE +/- 110264265.91, N = 3SE +/- 273721997.77, N = 3SE +/- 58489737.43, N = 3SE +/- 68861884.05, N = 3SE +/- 117940235.40, N = 32515396009971040098541572041358769271389037749131881941580002677532965101. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3K6K9K12K15KSE +/- 11.09, N = 3SE +/- 5.70, N = 3SE +/- 32.50, N = 3SE +/- 4.59, N = 3SE +/- 21.30, N = 3SE +/- 18.16, N = 313817.56019.211924.18056.810345.015483.51. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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/ao/real_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00527, N = 3SE +/- 0.00079, N = 3SE +/- 0.00266, N = 3SE +/- 0.00095, N = 3SE +/- 0.00442, N = 3SE +/- 0.00263, N = 37.571603.114936.046304.125995.633747.99661

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 313.515.6311.017.5410.0814.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X16M32M48M64M80MSE +/- 920101.18, N = 3SE +/- 407183.28, N = 3SE +/- 707337.29, N = 3SE +/- 324778.30, N = 9SE +/- 577386.15, N = 5SE +/- 370661.05, N = 37317448029952040555461553939872653336421767393181. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: CrownRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X816243240SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 334.0713.3926.1117.6625.5334.28MIN: 33.71 / MAX: 34.96MIN: 13.26 / MAX: 13.7MIN: 25.76 / MAX: 26.88MIN: 17.48 / MAX: 18.14MIN: 25.21 / MAX: 26.05MIN: 33.87 / MAX: 35.29

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_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00360, N = 3SE +/- 0.00183, N = 3SE +/- 0.00644, N = 3SE +/- 0.00262, N = 3SE +/- 0.00266, N = 3SE +/- 0.03487, N = 37.550983.109746.025334.107735.623327.94518

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 AtomsRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.44350.8871.33051.7742.2175SE +/- 0.00193, N = 3SE +/- 0.00129, N = 3SE +/- 0.00072, N = 3SE +/- 0.00017, N = 3SE +/- 0.00072, N = 3SE +/- 0.00180, N = 30.815741.970921.006661.487441.082740.77148

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: CrownRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 331.8812.5424.3016.5323.9031.87MIN: 31.52 / MAX: 32.48MIN: 12.4 / MAX: 12.78MIN: 24.1 / MAX: 24.75MIN: 16.29 / MAX: 16.93MIN: 23.65 / MAX: 24.33MIN: 31.55 / MAX: 32.69

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.03356, N = 3SE +/- 0.00858, N = 3SE +/- 0.07019, N = 13SE +/- 0.05564, N = 3SE +/- 0.03875, N = 3SE +/- 0.01772, N = 33.942329.040524.817516.870285.221783.55733MIN: 3.73MIN: 8.66MIN: 4.54MIN: 6.53MIN: 5.03MIN: 3.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X400800120016002000SE +/- 4.25, N = 3SE +/- 1.39, N = 3SE +/- 1.67, N = 3SE +/- 5.56, N = 3SE +/- 0.51, N = 3SE +/- 0.30, N = 31707.05730.501398.20942.041254.431855.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6001200180024003000SE +/- 0.69, N = 3SE +/- 5.29, N = 3SE +/- 1.85, N = 3SE +/- 0.49, N = 3SE +/- 0.65, N = 3SE +/- 1.22, N = 31215.852874.181431.032062.841559.981133.72MIN: 1205.62MIN: 2848.45MIN: 1419.84MIN: 2052.99MIN: 1553.13MIN: 1124.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.87841.75682.63523.51364.392SE +/- 0.033927, N = 3SE +/- 0.000146, N = 3SE +/- 0.005093, N = 3SE +/- 0.001267, N = 3SE +/- 0.012268, N = 3SE +/- 0.026958, N = 33.6965351.5420102.8038252.1658272.5608023.9041501. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 2.71, N = 3SE +/- 0.93, N = 3SE +/- 0.65, N = 3SE +/- 0.72, N = 3SE +/- 0.58, N = 3SE +/- 3.90, N = 3623.481445.76731.941026.63802.17577.36MIN: 612.64MIN: 1426.15MIN: 724.15MIN: 1018.25MIN: 797.8MIN: 566.151. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 1.01, N = 3SE +/- 4.30, N = 3SE +/- 0.45, N = 3SE +/- 1.05, N = 3SE +/- 1.43, N = 3SE +/- 1.83, N = 31012.45404.65738.48486.21791.99771.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

CloverLeaf

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1632486480SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 328.7771.6748.6969.4430.9646.811. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.11780.23560.35340.47120.589SE +/- 0.000412, N = 4SE +/- 0.001117, N = 4SE +/- 0.000580, N = 4SE +/- 0.000777, N = 4SE +/- 0.000079, N = 4SE +/- 0.000516, N = 40.2296390.5236910.2646710.3879940.2949630.210336MIN: 0.22MIN: 0.51MIN: 0.25MIN: 0.37MIN: 0.29MIN: 0.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 512Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.25072.50143.75215.00286.2535SE +/- 0.042581, N = 3SE +/- 0.004067, N = 3SE +/- 0.009412, N = 3SE +/- 0.006900, N = 3SE +/- 0.015310, N = 3SE +/- 0.044084, N = 35.2028202.2514503.9992463.1578173.6840215.5586661. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.343.116.024.155.637.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian DragonRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X816243240SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 333.7113.7625.9217.8625.8432.70MIN: 33.5 / MAX: 34.21MIN: 13.69 / MAX: 13.9MIN: 25.79 / MAX: 26.15MIN: 17.78 / MAX: 18.18MIN: 25.69 / MAX: 26.23MIN: 32.52 / MAX: 33.15

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer - Model: Asian Dragon ObjRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 330.3112.4523.2516.0723.3229.08MIN: 29.99 / MAX: 30.83MIN: 12.38 / MAX: 12.62MIN: 23.04 / MAX: 23.56MIN: 15.95 / MAX: 16.28MIN: 23.13 / MAX: 23.72MIN: 28.87 / MAX: 29.59

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 37.313.135.934.165.527.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 512Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.80121.60242.40363.20484.006SE +/- 0.014635, N = 3SE +/- 0.001407, N = 3SE +/- 0.002243, N = 3SE +/- 0.008125, N = 3SE +/- 0.001425, N = 3SE +/- 0.008262, N = 33.3550911.4888722.6273522.0714842.4569493.5606901. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

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 6.1Build: allmodconfigRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 0.65, N = 3SE +/- 0.17, N = 3SE +/- 0.30, N = 3SE +/- 0.34, N = 3SE +/- 0.53, N = 3SE +/- 0.24, N = 3516.661224.06649.96948.63673.54512.24

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 7.34VGR Performance MetricRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X90K180K270K360K450K4035181789713237592385182987624262881. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.58741.17481.76222.34962.937SE +/- 0.01363, N = 14SE +/- 0.01438, N = 5SE +/- 0.00626, N = 5SE +/- 0.01211, N = 5SE +/- 0.00974, N = 5SE +/- 0.01138, N = 51.097572.610851.543012.361191.157801.56158MIN: 0.93MIN: 2.48MIN: 1.44MIN: 2.28MIN: 1.07MIN: 1.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian DragonRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X918273645SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 337.2415.7429.0620.3529.5734.95MIN: 36.89 / MAX: 38.22MIN: 15.64 / MAX: 15.98MIN: 28.88 / MAX: 29.56MIN: 20.22 / MAX: 20.73MIN: 29.35 / MAX: 30.08MIN: 34.59 / MAX: 35.88

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.74791.49582.24372.99163.7395SE +/- 0.00164, N = 9SE +/- 0.00860, N = 9SE +/- 0.00137, N = 9SE +/- 0.00300, N = 9SE +/- 0.00341, N = 9SE +/- 0.00282, N = 91.513063.323791.798962.253462.013991.40617MIN: 1.46MIN: 2.96MIN: 1.7MIN: 2.11MIN: 1.97MIN: 1.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 331.7613.4324.7717.3625.2029.86MIN: 31.51 / MAX: 32.61MIN: 13.34 / MAX: 13.74MIN: 24.58 / MAX: 25.23MIN: 17.25 / MAX: 17.65MIN: 25 / MAX: 25.6MIN: 29.55 / MAX: 30.93

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1122334455SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.04, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 446.3621.6837.1528.1633.4550.92

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 - GriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X15003000450060007500SE +/- 58.70, N = 6SE +/- 18.56, N = 6SE +/- 19.61, N = 6SE +/- 24.15, N = 6SE +/- 46.73, N = 7SE +/- 42.46, N = 66888.462942.634992.693385.476033.856075.771. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.51, N = 15SE +/- 0.42, N = 3SE +/- 0.47, N = 10SE +/- 0.49, N = 4SE +/- 0.48, N = 8SE +/- 0.57, N = 1571.9833.3361.5143.4056.3677.151. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 298.51, N = 3SE +/- 237.39, N = 3SE +/- 131.80, N = 3SE +/- 188.30, N = 3SE +/- 75.96, N = 3SE +/- 85.31, N = 3179232.7881518.68148467.63109607.62135184.24188361.901. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.340.681.021.361.7SE +/- 0.007186, N = 15SE +/- 0.000252, N = 4SE +/- 0.003738, N = 4SE +/- 0.000514, N = 4SE +/- 0.001233, N = 4SE +/- 0.007237, N = 50.7222341.5111900.9746131.1458101.0675700.654945MIN: 0.64MIN: 1.44MIN: 0.92MIN: 1.1MIN: 1.03MIN: 0.591. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.74031.48062.22092.96123.7015SE +/- 0.01, N = 15SE +/- 0.02, N = 15SE +/- 0.03, N = 7SE +/- 0.02, N = 12SE +/- 0.01, N = 4SE +/- 0.05, N = 33.291.552.961.433.083.19MIN: 3.18 / MAX: 9.47MIN: 1.42 / MAX: 7.54MIN: 2.84 / MAX: 7.42MIN: 1.35 / MAX: 7.4MIN: 3.03 / MAX: 7.37MIN: 3.06 / MAX: 33.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X160320480640800SE +/- 0.13, N = 3SE +/- 0.31, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 3SE +/- 0.27, N = 3SE +/- 0.28, N = 3323.89743.23401.82585.86409.47328.89

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 1.3.1Benchmark: vklBenchmark ISPCRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X90180270360450SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3407179328230329409MIN: 53 / MAX: 5124MIN: 21 / MAX: 2742MIN: 42 / MAX: 4570MIN: 28 / MAX: 3431MIN: 39 / MAX: 4761MIN: 56 / MAX: 5419

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.76731.53462.30193.06923.8365SE +/- 0.01, N = 15SE +/- 0.03, N = 15SE +/- 0.03, N = 7SE +/- 0.01, N = 11SE +/- 0.01, N = 4SE +/- 0.04, N = 33.411.633.061.503.193.25MIN: 3.25 / MAX: 9.47MIN: 1.5 / MAX: 7.84MIN: 2.95 / MAX: 10.86MIN: 1.44 / MAX: 7.67MIN: 3.12 / MAX: 9.3MIN: 3.15 / MAX: 9.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1326395265SE +/- 0.08, N = 5SE +/- 0.03, N = 3SE +/- 0.07, N = 4SE +/- 0.10, N = 3SE +/- 0.03, N = 4SE +/- 0.06, N = 554.4526.3543.7233.9339.2759.81

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 100Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 87.07, N = 3SE +/- 59.93, N = 3SE +/- 234.97, N = 3SE +/- 52.22, N = 3SE +/- 26.01, N = 3SE +/- 413.17, N = 3177681.0783186.07147810.43110819.10134927.90188405.161. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

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 2023Implementation: MPI CPU - Input: water_GMX50_bareRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.60621.21241.81862.42483.031SE +/- 0.001, N = 3SE +/- 0.006, N = 3SE +/- 0.006, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.006, N = 32.6941.1922.2681.5472.2832.6081. (CXX) g++ options: -O3

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1020304050SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 441.8420.4934.7626.5631.2046.30

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 116.67, N = 3SE +/- 81.55, N = 3SE +/- 174.57, N = 3SE +/- 81.47, N = 3SE +/- 53.85, N = 3SE +/- 901.16, N = 3168262.8174596.44133655.2398019.87129547.31152268.171. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 98.23, N = 3SE +/- 213.27, N = 3SE +/- 151.91, N = 3SE +/- 80.81, N = 3SE +/- 56.06, N = 3SE +/- 186.86, N = 3175066.4078427.06142134.15104108.32132147.38173022.341. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Timed Node.js Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X130260390520650SE +/- 0.30, N = 3SE +/- 0.36, N = 3SE +/- 0.63, N = 3SE +/- 0.27, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 3269.14599.26330.17476.89337.73273.11

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 4.0Time To CompileRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X80160240320400SE +/- 0.22, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3168.86373.15207.82296.48212.94169.65

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.15.06Test: Memory CopyingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X17003400510068008500SE +/- 2.37, N = 3SE +/- 2.53, N = 3SE +/- 17.75, N = 3SE +/- 0.74, N = 3SE +/- 18.76, N = 3SE +/- 6.93, N = 37102.843512.676023.674667.355447.107725.731. (CC) gcc options: -std=gnu99 -O2 -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread

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 10Input: drivaerFastback, Small Mesh Size - Execution TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60120180240300124.42271.01172.51248.83139.48160.431. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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: leblancbigRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X816243240SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 316.8936.7625.0632.5519.3024.301. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X160320480640800SE +/- 2.40, N = 3SE +/- 3.59, N = 3SE +/- 3.39, N = 3SE +/- 4.75, N = 3SE +/- 0.47, N = 3SE +/- 1.01, N = 3355.89763.37424.14605.04439.27353.40

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.38, N = 3SE +/- 0.85, N = 3SE +/- 0.31, N = 3SE +/- 0.64, N = 3SE +/- 0.19, N = 3SE +/- 1.36, N = 3136.1363.38111.0782.80106.64136.831. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.0Time To CompileRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1020304050SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 322.0245.9926.1536.5527.5021.50

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40M80M120M160M200MSE +/- 67414.97, N = 3SE +/- 14437.61, N = 3SE +/- 73384.83, N = 3SE +/- 56665.69, N = 3SE +/- 118569.72, N = 3SE +/- 689894.03, N = 3188100333944633331630460001247760001493773332020823331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: VideoRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X7K14K21K28K35KSE +/- 370.51, N = 3SE +/- 128.60, N = 3SE +/- 343.95, N = 3SE +/- 195.46, N = 4SE +/- 762.84, N = 15SE +/- 248.27, N = 33370216769262491578231168254211. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

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 6.1Build: defconfigRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.39, N = 3SE +/- 0.27, N = 3SE +/- 0.33, N = 3SE +/- 0.52, N = 3SE +/- 0.39, N = 3SE +/- 0.28, N = 346.3296.3455.4977.0857.6945.70

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X4080120160200SE +/- 0.55, N = 14SE +/- 1.37, N = 3SE +/- 0.62, N = 3SE +/- 1.03, N = 3SE +/- 0.27, N = 3SE +/- 0.18, N = 376.27160.1790.74124.9593.0478.081. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 - DegriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2K4K6K8K10KSE +/- 77.53, N = 3SE +/- 40.41, N = 4SE +/- 0.00, N = 3SE +/- 42.25, N = 3SE +/- 84.09, N = 3SE +/- 0.00, N = 311010.705248.8510092.105788.7610008.0110710.001. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.15Time To CompileRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.10, N = 3SE +/- 0.80, N = 3SE +/- 0.46, N = 3SE +/- 0.26, N = 3SE +/- 0.62, N = 3SE +/- 0.77, N = 569.89144.6485.30114.6085.9769.76

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X40K80K120K160K200KSE +/- 382.02, N = 3SE +/- 206.12, N = 3SE +/- 101.82, N = 3SE +/- 82.20, N = 3SE +/- 502.29, N = 3SE +/- 280.05, N = 3188382910811566471139541549251837671. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60120180240300SE +/- 0.82, N = 10SE +/- 0.47, N = 8SE +/- 0.67, N = 10SE +/- 0.61, N = 9SE +/- 0.59, N = 10SE +/- 0.77, N = 15268.52144.60253.73187.73230.39297.381. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Server Rack - Acceleration: CPU-onlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.07070.14140.21210.28280.3535SE +/- 0.001, N = 14SE +/- 0.001, N = 13SE +/- 0.001, N = 14SE +/- 0.001, N = 14SE +/- 0.000, N = 14SE +/- 0.001, N = 140.1570.3140.1870.2480.1890.155

RocksDB

This is a benchmark of Meta/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 BetterRocksDB 8.0Test: Read While WritingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X900K1800K2700K3600K4500KSE +/- 51551.36, N = 3SE +/- 22094.66, N = 3SE +/- 15861.29, N = 3SE +/- 9341.69, N = 3SE +/- 19357.48, N = 3SE +/- 16167.79, N = 34284589215763734137652853572327310043689491. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -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.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3K6K9K12K15KSE +/- 101.60, N = 3SE +/- 0.00, N = 4SE +/- 116.93, N = 3SE +/- 59.02, N = 3SE +/- 124.23, N = 3SE +/- 84.50, N = 312698.206348.2811693.206787.1112175.6011577.501. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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: sedovbigRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1224364860SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 327.0954.1836.8546.6331.1534.671. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.84831.69662.54493.39324.2415SE +/- 0.01, N = 15SE +/- 0.02, N = 15SE +/- 0.08, N = 7SE +/- 0.04, N = 12SE +/- 0.02, N = 4SE +/- 0.05, N = 33.771.923.441.923.553.70MIN: 3.61 / MAX: 49.21MIN: 1.79 / MAX: 8.21MIN: 3.28 / MAX: 74.27MIN: 1.79 / MAX: 7.82MIN: 3.49 / MAX: 3.96MIN: 3.5 / MAX: 53.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1428425670SE +/- 0.39, N = 15SE +/- 0.55, N = 3SE +/- 0.59, N = 3SE +/- 0.71, N = 3SE +/- 1.26, N = 15SE +/- 0.36, N = 1532.5062.0442.4753.3140.3231.721. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X816243240SE +/- 0.20, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 15SE +/- 0.14, N = 3SE +/- 0.10, N = 334.4418.8530.4818.5728.8235.951. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: FastRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.029, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.019, N = 37.2184.0596.6915.0816.0887.8051. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 8 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.28, N = 5SE +/- 0.02, N = 4SE +/- 0.16, N = 5SE +/- 0.10, N = 4SE +/- 0.13, N = 5SE +/- 0.05, N = 570.0238.9164.7649.1359.5374.791. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 3.26, N = 3SE +/- 0.99, N = 3SE +/- 0.94, N = 3SE +/- 0.94, N = 3SE +/- 0.90, N = 3SE +/- 2.65, N = 31001.3523.5808.9561.1941.8856.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 7.92, N = 10SE +/- 0.64, N = 3SE +/- 3.12, N = 3SE +/- 1.90, N = 3SE +/- 5.44, N = 3SE +/- 5.55, N = 151036.7543.2862.8551.01031.0836.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

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 wrk 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 2.4.56Concurrent Requests: 1000Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3D50K100K150K200K250KSE +/- 1923.49, N = 3SE +/- 231.96, N = 3SE +/- 1686.11, N = 4SE +/- 1321.81, N = 6SE +/- 2209.61, N = 3223853.85117763.77140125.35134983.40163211.391. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Boat - Acceleration: CPU-onlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.991.982.973.964.95SE +/- 0.014, N = 9SE +/- 0.015, N = 7SE +/- 0.013, N = 9SE +/- 0.009, N = 8SE +/- 0.011, N = 9SE +/- 0.007, N = 102.4954.4002.7623.5332.9692.340

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered HalfspaceRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 2.08, N = 12SE +/- 0.22, N = 3SE +/- 0.43, N = 3SE +/- 0.86, N = 3SE +/- 0.49, N = 3SE +/- 0.55, N = 378.33147.0489.28120.7990.5878.431. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.05752.1153.17254.235.2875SE +/- 0.05, N = 15SE +/- 0.03, N = 15SE +/- 0.04, N = 7SE +/- 0.02, N = 12SE +/- 0.04, N = 4SE +/- 0.08, N = 34.702.854.192.624.364.65MIN: 4.42 / MAX: 107.07MIN: 2.55 / MAX: 9.26MIN: 4.02 / MAX: 10.5MIN: 2.43 / MAX: 8.76MIN: 4.27 / MAX: 7.21MIN: 4.46 / MAX: 47.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 4 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.28572.57143.85715.14286.4285SE +/- 0.009, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.005, N = 3SE +/- 0.011, N = 3SE +/- 0.016, N = 35.2923.2075.0933.9654.6045.7141. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1632486480SE +/- 1.11, N = 15SE +/- 0.10, N = 3SE +/- 0.33, N = 3SE +/- 0.64, N = 4SE +/- 0.21, N = 3SE +/- 0.66, N = 1543.0674.1344.3157.7846.2441.771. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 NanotubeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 0.41, N = 3SE +/- 0.68, N = 3SE +/- 0.38, N = 3SE +/- 0.65, N = 3SE +/- 0.39, N = 3SE +/- 0.04, N = 3126.80223.23150.84191.06143.85137.891. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1326395265SE +/- 0.70, N = 12SE +/- 0.50, N = 3SE +/- 0.27, N = 3SE +/- 0.09, N = 3SE +/- 0.22, N = 3SE +/- 0.47, N = 335.0159.1833.7145.6236.8134.161. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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_timeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 0.42, N = 3SE +/- 0.01, N = 3SE +/- 0.50, N = 3SE +/- 0.01, N = 3SE +/- 0.39, N = 3SE +/- 0.07, N = 3228.75142.44209.63166.64199.16249.60

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 4K - Video Preset: FasterRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.029, N = 3SE +/- 0.003, N = 3SE +/- 0.019, N = 3SE +/- 0.011, N = 3SE +/- 0.024, N = 3SE +/- 0.007, N = 314.1938.79113.48510.65212.36515.1331. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X900K1800K2700K3600K4500KSE +/- 6874.58, N = 3SE +/- 5512.56, N = 3SE +/- 4108.13, N = 3SE +/- 7348.92, N = 3SE +/- 3723.38, N = 3SE +/- 4728.17, N = 33982059.122439025.753646277.883221061.703510381.434124930.571. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: FastRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 321.9814.1321.7417.3519.7323.821. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:10Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X900K1800K2700K3600K4500KSE +/- 31974.02, N = 3SE +/- 8743.21, N = 3SE +/- 42060.16, N = 3SE +/- 8206.16, N = 3SE +/- 31345.84, N = 3SE +/- 50084.31, N = 33938540.032418021.173566082.943210247.223471647.554054196.001. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 wrk 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 2.4.56Concurrent Requests: 500Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3D50K100K150K200K250KSE +/- 1704.31, N = 3SE +/- 122.53, N = 3SE +/- 527.82, N = 3SE +/- 178.88, N = 3SE +/- 1520.67, N = 3230091.81137368.84158235.02161549.06177117.151. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 0.91, N = 9SE +/- 0.16, N = 7SE +/- 0.56, N = 8SE +/- 0.41, N = 8SE +/- 0.68, N = 8SE +/- 1.09, N = 9213.52131.32196.12157.56189.40217.161. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X70140210280350SE +/- 1.67, N = 3SE +/- 0.39, N = 3SE +/- 0.55, N = 3SE +/- 0.72, N = 3SE +/- 1.32, N = 3SE +/- 0.63, N = 3299.9182.3248.6195.6299.5254.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

RocksDB

This is a benchmark of Meta/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 BetterRocksDB 8.0Test: Read Random Write RandomRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X700K1400K2100K2800K3500KSE +/- 14308.15, N = 3SE +/- 20894.08, N = 3SE +/- 1917.12, N = 3SE +/- 2937.85, N = 3SE +/- 17306.41, N = 3SE +/- 2560.84, N = 33342984211349028205282675448269434734731401. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Xcompact3d Incompact3d

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

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.02, N = 4SE +/- 0.00, N = 3SE +/- 0.08, N = 4SE +/- 0.04, N = 3SE +/- 0.14, N = 4SE +/- 0.08, N = 412.5319.9014.6818.5812.5314.491. (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

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 0.33, N = 9SE +/- 0.33, N = 8SE +/- 0.38, N = 9SE +/- 0.37, N = 8SE +/- 0.64, N = 9SE +/- 0.40, N = 9214.84140.88202.87168.74193.06222.221. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Masskrug - Acceleration: CPU-onlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.92481.84962.77443.69924.624SE +/- 0.009, N = 9SE +/- 0.018, N = 8SE +/- 0.009, N = 9SE +/- 0.013, N = 8SE +/- 0.008, N = 9SE +/- 0.005, N = 92.6684.1102.9423.5232.9282.660

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:100Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X800K1600K2400K3200K4000KSE +/- 6589.95, N = 3SE +/- 1590.55, N = 3SE +/- 7441.98, N = 3SE +/- 10122.13, N = 3SE +/- 7626.67, N = 3SE +/- 13706.17, N = 33564857.902388901.553374511.843162482.243183961.703690970.441. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 - DegriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6001200180024003000SE +/- 16.51, N = 5SE +/- 15.74, N = 3SE +/- 50.07, N = 3SE +/- 9.12, N = 3SE +/- 40.19, N = 3SE +/- 9.49, N = 152960.621916.922766.952122.352927.902838.931. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X800K1600K2400K3200K4000KSE +/- 6280.08, N = 3SE +/- 1020.78, N = 3SE +/- 16289.33, N = 3SE +/- 3852.05, N = 3SE +/- 12961.93, N = 3SE +/- 9156.34, N = 33554398.242391691.963381093.613147488.473179844.533693334.621. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.09, N = 15SE +/- 0.12, N = 15SE +/- 0.16, N = 7SE +/- 0.09, N = 12SE +/- 0.08, N = 4SE +/- 0.23, N = 38.756.448.305.678.178.56MIN: 8.24 / MAX: 45.41MIN: 5.4 / MAX: 12.93MIN: 7.85 / MAX: 51.25MIN: 5.23 / MAX: 11.84MIN: 7.98 / MAX: 9.1MIN: 7.94 / MAX: 62.451. (CXX) g++ options: -O3 -rdynamic -lgomp -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 10Input: drivaerFastback, Small Mesh Size - Mesh TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X81624324024.3534.2324.8830.4026.1722.491. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:5Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X900K1800K2700K3600K4500KSE +/- 10711.98, N = 3SE +/- 5672.75, N = 3SE +/- 3998.91, N = 3SE +/- 15821.73, N = 3SE +/- 1748.55, N = 3SE +/- 8487.52, N = 33953637.222762729.113428414.423591302.953261982.164117576.041. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60120180240300180.59264.53201.08232.39196.48189.281. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Summer Nature 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X90180270360450SE +/- 1.07, N = 5SE +/- 0.06, N = 4SE +/- 3.53, N = 5SE +/- 0.30, N = 5SE +/- 0.63, N = 5SE +/- 2.95, N = 5402.89275.71368.45343.08366.43395.581. (CC) gcc options: -pthread

ASKAP

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

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X120240360480600SE +/- 2.05, N = 5SE +/- 0.91, N = 4SE +/- 0.48, N = 4SE +/- 0.73, N = 4SE +/- 0.97, N = 5SE +/- 1.79, N = 4547.68379.87439.08423.73552.49442.501. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.22, N = 7SE +/- 0.48, N = 6SE +/- 0.14, N = 7SE +/- 0.46, N = 6SE +/- 0.15, N = 7SE +/- 0.21, N = 7112.9986.31112.6791.94102.71122.991. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 10Input: drivaerFastback, Medium Mesh Size - Execution TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60012001800240030001849.382632.442170.642506.411913.592100.711. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.7Video Input: Bosphorus 1080p - Video Preset: FasterRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1020304050SE +/- 0.12, N = 4SE +/- 0.06, N = 3SE +/- 0.04, N = 4SE +/- 0.06, N = 4SE +/- 0.06, N = 4SE +/- 0.20, N = 442.2431.9443.0937.7639.9544.951. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 34.806.334.714.505.074.78MIN: 3.32 / MAX: 12.49MIN: 4.35 / MAX: 13.51MIN: 3.22 / MAX: 13.42MIN: 3.35 / MAX: 11.95MIN: 3.65 / MAX: 17.79MIN: 3.43 / MAX: 12.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: resizeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.040, N = 4SE +/- 0.032, N = 5SE +/- 0.069, N = 4SE +/- 0.027, N = 5SE +/- 0.100, N = 4SE +/- 0.126, N = 412.7969.55912.3269.50513.31312.244

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 DirectionRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.62, N = 3SE +/- 0.20, N = 3SE +/- 0.36, N = 3SE +/- 0.12, N = 3SE +/- 0.48, N = 3SE +/- 0.38, N = 358.2981.5067.0776.8861.3565.941. (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

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 322.0920.5024.0728.5121.7123.671. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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 - GriddingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 23.70, N = 5SE +/- 10.67, N = 3SE +/- 15.27, N = 3SE +/- 4.65, N = 3SE +/- 14.62, N = 3SE +/- 34.17, N = 152323.161687.082009.501784.982114.752148.451. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 37.899.888.128.227.5710.36MIN: 4.15 / MAX: 15.99MIN: 5.38 / MAX: 18.64MIN: 3.99 / MAX: 19.72MIN: 3.61 / MAX: 16.56MIN: 4.27 / MAX: 20.97MIN: 3.84 / MAX: 24.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Image ProcessingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20K40K60K80K100KSE +/- 750.41, N = 15SE +/- 959.48, N = 3SE +/- 315.95, N = 3SE +/- 383.74, N = 3SE +/- 764.22, N = 15SE +/- 840.30, N = 38153768959815366260685537798641. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X80160240320400SE +/- 0.37, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 1.32, N = 3SE +/- 0.25, N = 3SE +/- 0.42, N = 3305.98368.29279.40269.69308.86280.96MIN: 165.89 / MAX: 315MIN: 193.61 / MAX: 387.71MIN: 178.37 / MAX: 291.55MIN: 197.15 / MAX: 279.39MIN: 298.12 / MAX: 320.39MIN: 147.36 / MAX: 288.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X70140210280350SE +/- 1.89, N = 3SE +/- 0.72, N = 3SE +/- 4.91, N = 3SE +/- 0.98, N = 3SE +/- 2.69, N = 4SE +/- 2.59, N = 3314.37230.63286.69252.60303.04276.80MIN: 15.78 / MAX: 10000MIN: 8.23 / MAX: 8571.43MIN: 16.3 / MAX: 12000MIN: 11.25 / MAX: 10000MIN: 14.81 / MAX: 12000MIN: 15.24 / MAX: 12000

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Server Room - Acceleration: CPU-onlyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.71511.43022.14532.86043.5755SE +/- 0.008, N = 9SE +/- 0.011, N = 8SE +/- 0.005, N = 9SE +/- 0.006, N = 9SE +/- 0.007, N = 9SE +/- 0.005, N = 92.3473.1782.5022.7902.4942.332

RocksDB

This is a benchmark of Meta/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 BetterRocksDB 8.0Test: Update RandomRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X200K400K600K800K1000KSE +/- 2456.99, N = 3SE +/- 2736.72, N = 3SE +/- 2015.96, N = 3SE +/- 988.06, N = 3SE +/- 616.11, N = 3SE +/- 4634.57, N = 39588527271888445218372168099309897301. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X70140210280350SE +/- 1.34, N = 3SE +/- 2.82, N = 3SE +/- 1.26, N = 3SE +/- 1.65, N = 3SE +/- 3.38, N = 4SE +/- 2.09, N = 3312.03230.06281.89251.53301.88275.51MIN: 16.36 / MAX: 10000MIN: 8.13 / MAX: 10000MIN: 16.21 / MAX: 10000MIN: 11.12 / MAX: 10000MIN: 14.88 / MAX: 10000MIN: 15.29 / MAX: 12000

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X6001200180024003000SE +/- 6.69, N = 3SE +/- 4.33, N = 3SE +/- 3.18, N = 3SE +/- 1.00, N = 3SE +/- 12.98, N = 3SE +/- 3.61, N = 32866212528142799219221281. firefox 111.0.1

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.47, N = 15SE +/- 0.05, N = 15SE +/- 0.54, N = 7SE +/- 0.08, N = 12SE +/- 0.12, N = 4SE +/- 0.21, N = 383.99104.5082.7692.9193.6477.83MIN: 80.13 / MAX: 96.76MIN: 103.57 / MAX: 122.52MIN: 80.59 / MAX: 95.97MIN: 91.95 / MAX: 100.2MIN: 89.62 / MAX: 106.59MIN: 77.15 / MAX: 95.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.987.185.485.366.045.52MIN: 3.08 / MAX: 18.15MIN: 3.73 / MAX: 14.62MIN: 2.77 / MAX: 12.72MIN: 2.76 / MAX: 11.96MIN: 3.19 / MAX: 18.63MIN: 2.89 / MAX: 13.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X150300450600750SE +/- 0.13, N = 3SE +/- 1.27, N = 3SE +/- 0.26, N = 3SE +/- 0.33, N = 3SE +/- 0.21, N = 3SE +/- 0.40, N = 3590.69707.51543.31529.80593.74551.98MIN: 302.36 / MAX: 616.81MIN: 362.92 / MAX: 733.73MIN: 272.82 / MAX: 567.91MIN: 298.06 / MAX: 545.08MIN: 576.33 / MAX: 610.99MIN: 286.07 / MAX: 578.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 3.90, N = 3SE +/- 2.11, N = 3SE +/- 3.00, N = 3SE +/- 2.87, N = 3SE +/- 2.02, N = 3SE +/- 1.27, N = 31082.511281.59992.01960.701058.961039.19MIN: 942.47 / MAX: 1278.39MIN: 1072.55 / MAX: 1386.43MIN: 593.33 / MAX: 1135.95MIN: 853.94 / MAX: 1054.88MIN: 943.8 / MAX: 1194.07MIN: 603.68 / MAX: 1231.91. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.10, N = 15SE +/- 0.10, N = 15SE +/- 0.10, N = 7SE +/- 0.10, N = 12SE +/- 0.27, N = 4SE +/- 0.27, N = 311.909.5911.919.3511.6612.46MIN: 11.04 / MAX: 71.93MIN: 8.75 / MAX: 17MIN: 11.32 / MAX: 29.07MIN: 8.66 / MAX: 16MIN: 10.93 / MAX: 12.45MIN: 11.85 / MAX: 54.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 39.998.7410.8211.619.8410.881. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 5.33, N = 3SE +/- 5.72, N = 3SE +/- 9.17, N = 3SE +/- 5.33, N = 3SE +/- 3.83, N = 3SE +/- 1.96, N = 31086.141272.191004.91957.751079.721054.73MIN: 882.23 / MAX: 1289.62MIN: 756.21 / MAX: 1386.95MIN: 641.97 / MAX: 1152.07MIN: 577.87 / MAX: 1051.92MIN: 573.65 / MAX: 1225.15MIN: 584.15 / MAX: 1252.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60120180240300SE +/- 1.96, N = 3SE +/- 1.01, N = 3SE +/- 0.86, N = 3SE +/- 1.75, N = 3SE +/- 2.81, N = 4SE +/- 2.36, N = 3284.21215.22255.89229.19268.00247.72MIN: 13.26 / MAX: 8571.43MIN: 8.16 / MAX: 8571.43MIN: 15.79 / MAX: 8571.43MIN: 10.92 / MAX: 10000MIN: 14.53 / MAX: 10000MIN: 12.58 / MAX: 8571.43

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.08, N = 15SE +/- 0.06, N = 15SE +/- 0.08, N = 7SE +/- 0.09, N = 12SE +/- 0.10, N = 4SE +/- 0.04, N = 39.277.288.437.029.109.23MIN: 8.73 / MAX: 47.39MIN: 6.76 / MAX: 13.64MIN: 8.01 / MAX: 14.61MIN: 6.46 / MAX: 13.43MIN: 8.79 / MAX: 37.18MIN: 9 / MAX: 53.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X7001400210028003500SE +/- 7.88, N = 3SE +/- 7.54, N = 3SE +/- 13.54, N = 3SE +/- 4.36, N = 3SE +/- 6.89, N = 3SE +/- 1.15, N = 33159242531383121317524121. chrome 111.0.5563.110

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1428425670SE +/- 0.16, N = 3SE +/- 0.86, N = 3SE +/- 0.14, N = 3SE +/- 0.37, N = 3SE +/- 0.10, N = 3SE +/- 0.58, N = 358.7263.1253.9948.2956.2458.42MIN: 29.06 / MAX: 69.83MIN: 42.47 / MAX: 73.34MIN: 27.76 / MAX: 63.22MIN: 27.04 / MAX: 61.6MIN: 46.11 / MAX: 67.65MIN: 29.2 / MAX: 68.611. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: unsharp-maskRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.04, N = 4SE +/- 0.00, N = 5SE +/- 0.01, N = 4SE +/- 0.07, N = 5SE +/- 0.04, N = 4SE +/- 0.01, N = 413.1610.1412.4110.2312.9412.44

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 0 - Input: Bosphorus 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.15, N = 1519.7817.2521.3222.3719.3321.821. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: Points2ImageRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X9K18K27K36K45KSE +/- 154.29, N = 3SE +/- 591.48, N = 3SE +/- 167.57, N = 3SE +/- 314.26, N = 3SE +/- 316.23, N = 3SE +/- 295.31, N = 333484.3743360.5935526.6741450.6534161.8535141.541. (CXX) g++ options: -O3 -std=c++11 -fopenmp

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 15SE +/- 0.00, N = 3SE +/- 0.13, N = 15SE +/- 0.14, N = 515.011.712.811.614.412.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.23082.46163.69244.92326.154SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.685.474.294.244.784.30MIN: 2.86 / MAX: 14.55MIN: 3.44 / MAX: 15.09MIN: 2.71 / MAX: 11.96MIN: 2.52 / MAX: 12.88MIN: 3.46 / MAX: 16.59MIN: 2.7 / MAX: 12.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 wrk 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 2.4.56Concurrent Requests: 200Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3D50K100K150K200K250KSE +/- 778.22, N = 3SE +/- 8.76, N = 3SE +/- 434.31, N = 3SE +/- 1030.94, N = 3SE +/- 390.67, N = 3204101.12164764.69211000.52202785.74204878.181. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.13Speed: Speed 5 - Input: Bosphorus 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1122334455SE +/- 0.05, N = 4SE +/- 0.13, N = 4SE +/- 0.26, N = 4SE +/- 0.16, N = 4SE +/- 0.13, N = 4SE +/- 0.16, N = 440.1349.9743.6449.7539.1043.761. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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 wrk 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 2.4.56Concurrent Requests: 100Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3D40K80K120K160K200KSE +/- 596.08, N = 3SE +/- 51.74, N = 3SE +/- 526.72, N = 3SE +/- 110.57, N = 3SE +/- 1107.24, N = 3164236.15157972.36156497.14198848.67185877.551. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

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 1.5.6Model: Church FacadeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10002000300040005000SE +/- 4.07, N = 8SE +/- 7.77, N = 7SE +/- 6.18, N = 7SE +/- 3.24, N = 7SE +/- 5.87, N = 8SE +/- 4.69, N = 73614451445764488364744001. (CXX) g++ options: -O3

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Summer Nature 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 1.20, N = 10SE +/- 3.14, N = 9SE +/- 2.36, N = 10SE +/- 1.92, N = 10SE +/- 0.87, N = 10SE +/- 2.93, N = 101409.201199.851382.591440.051269.551509.371. (CC) gcc options: -pthread

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: EigenRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X400800120016002000SE +/- 20.63, N = 3SE +/- 7.31, N = 3SE +/- 6.12, N = 3SE +/- 2.33, N = 3SE +/- 6.66, N = 3SE +/- 14.31, N = 31857148417441539177217681. (CXX) g++ options: -flto -pthread

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X4080120160200SE +/- 2.15, N = 3SE +/- 1.01, N = 3SE +/- 0.70, N = 3SE +/- 0.10, N = 3SE +/- 3.40, N = 12SE +/- 0.06, N = 3186.00151.11174.83153.11188.84167.141. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Graph APIRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30K60K90K120K150KSE +/- 856.06, N = 3SE +/- 517.47, N = 3SE +/- 464.42, N = 3SE +/- 721.51, N = 3SE +/- 1219.53, N = 3SE +/- 1720.08, N = 31392841136001236051117731388391220651. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X612182430SE +/- 0.34, N = 15SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.33, N = 15SE +/- 0.07, N = 325.320.423.420.525.223.51. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.17, N = 15SE +/- 0.15, N = 15SE +/- 0.03, N = 7SE +/- 0.17, N = 12SE +/- 0.31, N = 4SE +/- 0.15, N = 314.8312.8114.0312.2714.6715.19MIN: 13.58 / MAX: 70.75MIN: 11.56 / MAX: 20.25MIN: 13.69 / MAX: 20.11MIN: 11.1 / MAX: 20.03MIN: 14.02 / MAX: 22MIN: 13.93 / MAX: 77.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.12952.2593.38854.5185.6475SE +/- 0.06, N = 15SE +/- 0.03, N = 15SE +/- 0.07, N = 7SE +/- 0.06, N = 12SE +/- 0.09, N = 4SE +/- 0.15, N = 34.374.404.734.274.075.02MIN: 4.03 / MAX: 11.7MIN: 4.18 / MAX: 10.81MIN: 4.46 / MAX: 10.76MIN: 3.85 / MAX: 14.57MIN: 3.93 / MAX: 9.02MIN: 4.59 / MAX: 13.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.09, N = 15SE +/- 0.11, N = 15SE +/- 0.08, N = 7SE +/- 0.08, N = 12SE +/- 0.03, N = 4SE +/- 0.05, N = 36.816.727.086.036.417.40MIN: 6.41 / MAX: 35.28MIN: 5.86 / MAX: 14.93MIN: 6.81 / MAX: 42.71MIN: 5.54 / MAX: 11.95MIN: 6.29 / MAX: 8.71MIN: 7.09 / MAX: 46.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: UploadRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X918273645SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 334.5231.1335.9733.5132.6837.511. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: UploadRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 373.1581.1170.2075.3577.2667.321. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: BLASRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X400800120016002000SE +/- 19.14, N = 3SE +/- 22.14, N = 3SE +/- 4.84, N = 3SE +/- 1.86, N = 3SE +/- 6.93, N = 3SE +/- 21.70, N = 31894159619091685188518951. (CXX) g++ options: -flto -pthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.16, N = 15SE +/- 0.16, N = 15SE +/- 0.14, N = 7SE +/- 0.13, N = 12SE +/- 0.33, N = 4SE +/- 0.38, N = 312.2911.7212.3210.7412.3512.83MIN: 11.39 / MAX: 46.78MIN: 10.57 / MAX: 19.6MIN: 11.71 / MAX: 43.73MIN: 9.53 / MAX: 17.28MIN: 11.6 / MAX: 19.3MIN: 11.77 / MAX: 58.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: PlatformRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 370.8064.6973.5469.0467.3177.151. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: PlatformRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3106.99117.10103.01109.72112.5498.191. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On DemandRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.31, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3106.58117.00102.84109.64112.7198.221. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On DemandRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.21, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 371.0864.7573.6669.0967.2177.121. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: auto-levelsRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.066, N = 4SE +/- 0.007, N = 5SE +/- 0.015, N = 5SE +/- 0.009, N = 5SE +/- 0.041, N = 5SE +/- 0.010, N = 510.8359.20510.0289.09810.60010.059

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.15750.3150.47250.630.7875SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.670.700.600.590.680.61MIN: 0.36 / MAX: 7.69MIN: 0.33 / MAX: 15.32MIN: 0.33 / MAX: 7.73MIN: 0.33 / MAX: 9.46MIN: 0.37 / MAX: 12.44MIN: 0.34 / MAX: 9.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Features 2DRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X8K16K24K32K40KSE +/- 88.66, N = 3SE +/- 308.26, N = 3SE +/- 229.68, N = 3SE +/- 58.62, N = 3SE +/- 332.34, N = 3SE +/- 241.97, N = 33543433758342143121637002338281. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Chimera 1080pRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 0.84, N = 5SE +/- 0.58, N = 5SE +/- 1.78, N = 5SE +/- 2.08, N = 5SE +/- 0.15, N = 5SE +/- 0.87, N = 5913.12876.16943.851011.83861.74991.481. (CC) gcc options: -pthread

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 37.598.338.218.447.328.411. (CXX) g++ options: -O3

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: StitchingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30K60K90K120K150KSE +/- 352.62, N = 3SE +/- 223.20, N = 3SE +/- 363.44, N = 3SE +/- 221.94, N = 3SE +/- 1677.00, N = 3SE +/- 1257.43, N = 31204521114901146291074071233641110071. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Crafty

This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3M6M9M12M15MSE +/- 101052.94, N = 15SE +/- 12046.55, N = 4SE +/- 8893.12, N = 4SE +/- 32233.35, N = 4SE +/- 163590.17, N = 15SE +/- 39367.46, N = 41456669414830582145103381512565913447511154319051. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.08780.17560.26340.35120.439SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.390.350.350.340.390.35MIN: 0.23 / MAX: 7.62MIN: 0.21 / MAX: 7.11MIN: 0.21 / MAX: 7.37MIN: 0.21 / MAX: 6.87MIN: 0.23 / MAX: 11.68MIN: 0.21 / MAX: 7.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPURyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.115.615.465.366.145.52MIN: 3.23 / MAX: 13.47MIN: 2.83 / MAX: 12.74MIN: 2.86 / MAX: 11.9MIN: 2.84 / MAX: 11.88MIN: 3.27 / MAX: 20.78MIN: 2.91 / MAX: 16.11. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 1.5.6Model: LionRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X8001600240032004000SE +/- 6.54, N = 8SE +/- 5.25, N = 8SE +/- 11.99, N = 8SE +/- 2.56, N = 8SE +/- 6.29, N = 8SE +/- 10.95, N = 83150352635853498354534431. (CXX) g++ options: -O3

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X80160240320400SE +/- 3.25, N = 3SE +/- 1.03, N = 3SE +/- 0.60, N = 3SE +/- 1.24, N = 3SE +/- 2.32, N = 3SE +/- 2.58, N = 3329.35360.05346.17366.44322.63347.401. chrome 111.0.5563.110

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: LiveRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 327.6728.9126.1627.1128.4925.551. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: LiveRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X4080120160200SE +/- 0.80, N = 3SE +/- 0.54, N = 3SE +/- 0.74, N = 3SE +/- 0.26, N = 3SE +/- 0.80, N = 3SE +/- 0.39, N = 3182.49174.70193.02186.28177.25197.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: CoreRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X10K20K30K40K50KSE +/- 129.20, N = 3SE +/- 126.98, N = 3SE +/- 93.86, N = 3SE +/- 167.47, N = 3SE +/- 664.15, N = 15SE +/- 517.12, N = 34682041495426604139743067416021. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 39.239.969.8010.138.9710.051. (CXX) g++ options: -O3

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: rotateRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.016, N = 5SE +/- 0.004, N = 5SE +/- 0.011, N = 5SE +/- 0.066, N = 5SE +/- 0.008, N = 5SE +/- 0.015, N = 59.1648.8678.9218.8749.7678.727

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 38.859.629.419.759.819.891. (CXX) g++ options: -O3

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X612182430SE +/- 0.22, N = 15SE +/- 0.27, N = 15SE +/- 0.19, N = 7SE +/- 0.17, N = 12SE +/- 0.25, N = 4SE +/- 0.49, N = 325.1227.2324.7925.0924.4125.76MIN: 23.5 / MAX: 69.69MIN: 25.47 / MAX: 46.51MIN: 23.78 / MAX: 103.04MIN: 23.53 / MAX: 32.47MIN: 23.76 / MAX: 35.62MIN: 24 / MAX: 67.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X80160240320400SE +/- 2.50, N = 3SE +/- 0.58, N = 4SE +/- 2.36, N = 3SE +/- 0.81, N = 3SE +/- 2.74, N = 3SE +/- 0.87, N = 4378.7349.1349.9344.6380.5346.01. chrome 111.0.5563.110

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X120240360480600SE +/- 5.78, N = 15SE +/- 1.58, N = 4SE +/- 2.29, N = 4SE +/- 1.35, N = 4SE +/- 2.16, N = 4SE +/- 0.85, N = 4556513513504520510

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 19.59, N = 15SE +/- 4.49, N = 3SE +/- 7.38, N = 3SE +/- 2.34, N = 3SE +/- 25.42, N = 15SE +/- 6.76, N = 31981.12108.22175.52154.72062.82124.51. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3D50100150200250SE +/- 0.86, N = 3SE +/- 2.30, N = 3SE +/- 1.17, N = 3SE +/- 0.89, N = 3SE +/- 1.84, N = 3198.86208.30203.57207.59189.721. firefox 111.0.1

Benchmark: Jetstream 2 - Browser: Firefox

Ryzen 9 7950X: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.1Video Input: Chimera 1080p 10-bitRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 0.47, N = 5SE +/- 0.57, N = 5SE +/- 1.56, N = 5SE +/- 5.31, N = 5SE +/- 1.18, N = 5SE +/- 5.76, N = 5831.74800.69839.58865.98789.57865.981. (CC) gcc options: -pthread

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.4140.8281.2421.6562.07SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 13SE +/- 0.00, N = 31.711.831.781.841.681.831. (CXX) g++ options: -O3

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X110220330440550SE +/- 5.32, N = 15SE +/- 3.77, N = 3SE +/- 5.61, N = 4SE +/- 0.95, N = 3SE +/- 4.91, N = 15SE +/- 1.24, N = 3502.3467.8479.9464.0507.4482.81. firefox 111.0.1

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: Euclidean ClusterRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 14.88, N = 5SE +/- 0.86, N = 5SE +/- 2.58, N = 5SE +/- 3.57, N = 5SE +/- 4.87, N = 5SE +/- 3.08, N = 52207.792118.192310.292281.332173.132315.401. (CXX) g++ options: -O3 -std=c++11 -fopenmp

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X246810SE +/- 0.04, N = 13SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.555.876.055.935.965.891. (CXX) g++ options: -O3

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X400800120016002000SE +/- 60.64, N = 3SE +/- 60.40, N = 3SE +/- 2.86, N = 15SE +/- 3.63, N = 3SE +/- 21.62, N = 15SE +/- 4.32, N = 51897.01941.41953.12028.11860.92012.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: LiveRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 316.8016.2016.0816.1017.2815.871. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: LiveRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X70140210280350SE +/- 1.05, N = 3SE +/- 0.53, N = 3SE +/- 0.65, N = 3SE +/- 1.14, N = 3SE +/- 1.96, N = 3SE +/- 0.55, N = 3300.57311.68314.12313.66292.31318.241. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous Suite 2021.11.02Backend: OpenMP - Kernel: NDT MappingRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 10.82, N = 15SE +/- 2.72, N = 4SE +/- 3.30, N = 3SE +/- 1.53, N = 4SE +/- 2.10, N = 4SE +/- 1.27, N = 41424.881498.881462.041510.771397.771472.061. (CXX) g++ options: -O3 -std=c++11 -fopenmp

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: PlatformRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.52, N = 3SE +/- 0.07, N = 3SE +/- 0.30, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3SE +/- 0.10, N = 3110.22106.77105.92104.91112.19104.251. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: PlatformRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1632486480SE +/- 0.32, N = 3SE +/- 0.04, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 368.7370.9571.5272.2067.5272.661. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On DemandRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.38, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.24, N = 3SE +/- 0.05, N = 3109.66107.06105.99104.77111.70104.081. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: Video On DemandRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1632486480SE +/- 0.24, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 369.0870.7571.4772.3067.8272.781. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: UploadRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 318.0318.4718.5718.8617.6018.881. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: UploadRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X306090120150SE +/- 0.33, N = 3SE +/- 0.18, N = 3SE +/- 0.63, N = 3SE +/- 0.13, N = 3SE +/- 0.49, N = 3SE +/- 0.10, N = 3140.05136.74135.99133.86143.46133.741. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.31, N = 15SE +/- 0.02, N = 5SE +/- 0.23, N = 3SE +/- 0.04, N = 5SE +/- 0.06, N = 5SE +/- 0.10, N = 518.917.917.917.718.118.11. firefox 111.0.1

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X70140210280350SE +/- 2.89, N = 3SE +/- 0.81, N = 3SE +/- 2.10, N = 3SE +/- 3.72, N = 3SE +/- 4.00, N = 3SE +/- 0.39, N = 3294.8311.2304.6307.4291.5304.81. firefox 111.0.1

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: FirefoxRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X60120180240300SE +/- 0.64, N = 4SE +/- 0.07, N = 3SE +/- 2.88, N = 4SE +/- 0.06, N = 4SE +/- 1.63, N = 4SE +/- 2.24, N = 4260.1249.7245.0246.0245.4244.71. firefox 111.0.1

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X90180270360450SE +/- 3.46, N = 3SE +/- 1.76, N = 3SE +/- 2.52, N = 3SE +/- 1.15, N = 3SE +/- 2.19, N = 3SE +/- 1.67, N = 33823953954023793991. chrome 111.0.5563.110

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X714212835SE +/- 0.15, N = 13SE +/- 0.01, N = 13SE +/- 0.15, N = 13SE +/- 0.02, N = 13SE +/- 0.29, N = 15SE +/- 0.06, N = 1327.5527.5327.4727.9126.3427.921. (CC) gcc options: -fvisibility=hidden -O2 -lm

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 2.89, N = 15SE +/- 0.02, N = 4SE +/- 0.88, N = 4SE +/- 0.06, N = 4SE +/- 2.93, N = 15SE +/- 0.05, N = 5229.47230.42220.88226.11230.91217.971. chrome 111.0.5563.110

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X300K600K900K1200K1500KSE +/- 9474.53, N = 4SE +/- 12214.58, N = 4SE +/- 3277.14, N = 4SE +/- 12733.05, N = 5SE +/- 6424.80, N = 4SE +/- 6959.54, N = 4122630112166551262058124344512075001257538

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.23752.4753.71254.956.1875SE +/- 0.02, N = 8SE +/- 0.00, N = 8SE +/- 0.05, N = 8SE +/- 0.01, N = 8SE +/- 0.05, N = 15SE +/- 0.01, N = 85.465.395.505.485.275.401. (CC) gcc options: -fvisibility=hidden -O2 -lm

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 BenchmarkRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X2004006008001000SE +/- 3.90, N = 3SE +/- 2.61, N = 3SE +/- 6.04, N = 3SE +/- 3.65, N = 3SE +/- 5.29, N = 3SE +/- 6.18, N = 3945.79946.66934.87964.34924.61945.33

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 7.3.0Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.08252.1653.24754.335.4125SE +/- 0.033, N = 8SE +/- 0.006, N = 8SE +/- 0.012, N = 8SE +/- 0.005, N = 8SE +/- 0.018, N = 8SE +/- 0.010, N = 84.7104.6774.8114.6654.7914.616

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100Ryzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.04, N = 12SE +/- 0.01, N = 12SE +/- 0.09, N = 12SE +/- 0.01, N = 12SE +/- 0.12, N = 15SE +/- 0.02, N = 1217.2417.0917.5817.3816.8817.281. (CC) gcc options: -fvisibility=hidden -O2 -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 8.69, N = 3SE +/- 4.29, N = 3SE +/- 35.99, N = 3SE +/- 4.81, N = 3SE +/- 4.35, N = 3SE +/- 6.06, N = 32488.22451.62419.62465.42426.52463.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 6.71, N = 10SE +/- 1.54, N = 3SE +/- 1.55, N = 3SE +/- 7.19, N = 3SE +/- 8.46, N = 3SE +/- 3.94, N = 152404.22359.72397.82389.32343.72369.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression SpeedRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5001000150020002500SE +/- 13.71, N = 3SE +/- 6.14, N = 3SE +/- 9.40, N = 3SE +/- 10.67, N = 3SE +/- 1.83, N = 3SE +/- 14.03, N = 32410.02396.92421.92413.62369.82392.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural NetworkRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5K10K15K20K25KSE +/- 790.39, N = 15SE +/- 150.52, N = 15SE +/- 417.75, N = 15SE +/- 180.65, N = 15SE +/- 523.21, N = 15SE +/- 416.06, N = 152183312528230721236624081195281. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: Object DetectionRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X5K10K15K20K25KSE +/- 582.17, N = 12SE +/- 251.59, N = 3SE +/- 426.83, N = 12SE +/- 300.73, N = 15SE +/- 448.53, N = 12SE +/- 433.40, N = 152003223570207642249719800194431. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google ChromeRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.35, N = 15SE +/- 0.02, N = 6SE +/- 0.12, N = 6SE +/- 0.02, N = 6SE +/- 0.42, N = 15SE +/- 0.29, N = 1518.8117.5417.3717.3019.1317.841. chrome 111.0.5563.110

Benchmark: StyleBench - Browser: Google Chrome

Ryzen 9 7950X: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Ryzen 9 7900X3D: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Ryzen 7 7700X: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Ryzen 9 7900X: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Ryzen 5 7600X: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Ryzen 9 7950X3D: The test quit with a non-zero exit status. E: selenium.common.exceptions.WebDriverException: Message: unknown error: net::ERR_NAME_NOT_RESOLVED

Benchmark: StyleBench - Browser: Firefox

Ryzen 9 7950X: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

Ryzen 9 7900X3D: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

Ryzen 7 7700X: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

Ryzen 9 7900X: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

Ryzen 5 7600X: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

Ryzen 9 7950X3D: The test quit with a non-zero exit status. E: ERROR: test_untitled_test_case (__main__.UntitledTestCase.test_untitled_test_case)

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.60, N = 15SE +/- 0.05, N = 3SE +/- 0.52, N = 15SE +/- 0.03, N = 3SE +/- 0.59, N = 15SE +/- 0.47, N = 1515.5415.8516.5815.0016.8416.111. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1530456075SE +/- 2.37, N = 15SE +/- 0.19, N = 3SE +/- 1.82, N = 15SE +/- 0.14, N = 3SE +/- 2.12, N = 15SE +/- 1.79, N = 1565.6163.0861.1266.6760.4062.791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X3691215SE +/- 0.35240, N = 15SE +/- 0.37638, N = 12SE +/- 0.32714, N = 15SE +/- 0.08015, N = 4SE +/- 0.41714, N = 15SE +/- 0.00280, N = 36.4681810.345647.079616.541587.528624.307231. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X50100150200250SE +/- 9.73, N = 15SE +/- 2.71, N = 12SE +/- 6.88, N = 15SE +/- 1.83, N = 4SE +/- 7.44, N = 15SE +/- 0.15, N = 3161.9797.74145.66152.92138.59232.151. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.70151.4032.10452.8063.5075SE +/- 0.03598, N = 15SE +/- 0.04474, N = 15SE +/- 0.04702, N = 15SE +/- 0.00807, N = 3SE +/- 0.07174, N = 12SE +/- 0.04997, N = 152.111603.117722.242692.625052.357302.156591. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X100200300400500SE +/- 7.87, N = 15SE +/- 4.29, N = 15SE +/- 8.88, N = 15SE +/- 1.17, N = 3SE +/- 11.89, N = 12SE +/- 10.64, N = 15475.36321.55448.40380.87428.15467.031. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X816243240SE +/- 0.90, N = 15SE +/- 2.57, N = 15SE +/- 1.07, N = 15SE +/- 1.83, N = 15SE +/- 0.30, N = 3SE +/- 0.09, N = 324.9536.7225.9132.3935.6326.481. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X918273645SE +/- 1.45, N = 15SE +/- 1.68, N = 15SE +/- 1.57, N = 15SE +/- 2.09, N = 15SE +/- 0.24, N = 3SE +/- 0.12, N = 340.8128.8739.5132.5228.0737.761. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X150300450600750SE +/- 0.41, N = 3SE +/- 53.52, N = 13SE +/- 30.37, N = 15SE +/- 0.38, N = 3SE +/- 13.38, N = 13SE +/- 0.15, N = 3275.94678.05463.80460.09368.22273.951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.82131.64262.46393.28524.1065SE +/- 0.005330, N = 3SE +/- 0.080293, N = 13SE +/- 0.149914, N = 15SE +/- 0.001812, N = 3SE +/- 0.073837, N = 13SE +/- 0.002007, N = 33.6240201.5508782.2928802.1735002.7478803.6503301. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X0.29360.58720.88081.17441.468SE +/- 0.033176, N = 15SE +/- 0.005373, N = 3SE +/- 0.028899, N = 15SE +/- 0.001823, N = 3SE +/- 0.005381, N = 3SE +/- 0.023858, N = 150.9182021.3047900.9750821.2282001.1165200.8568731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X30060090012001500SE +/- 40.93, N = 15SE +/- 3.13, N = 3SE +/- 31.13, N = 15SE +/- 1.22, N = 3SE +/- 4.31, N = 3SE +/- 30.58, N = 151109.31766.181038.03813.89895.201178.411. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1632486480SE +/- 1.95, N = 15SE +/- 6.36, N = 15SE +/- 3.08, N = 15SE +/- 4.71, N = 15SE +/- 2.52, N = 15SE +/- 2.08, N = 1562.5873.5763.5858.3257.8552.621. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X510152025SE +/- 0.56, N = 15SE +/- 0.98, N = 15SE +/- 0.82, N = 15SE +/- 1.24, N = 15SE +/- 0.58, N = 15SE +/- 0.71, N = 1516.2314.7716.2818.5417.6419.401. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X20406080100SE +/- 0.12, N = 3SE +/- 7.82, N = 15SE +/- 3.47, N = 15SE +/- 0.97, N = 3SE +/- 4.94, N = 15SE +/- 3.14, N = 1582.12109.4193.0370.21107.4388.241. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: yolov4 - Device: CPU - Executor: StandardRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X48121620SE +/- 0.01808, N = 3SE +/- 0.58506, N = 15SE +/- 0.36208, N = 15SE +/- 0.19437, N = 3SE +/- 0.46030, N = 15SE +/- 0.36386, N = 1512.177509.7255710.9377714.248009.6042011.513731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetRyzen 9 7950X3DRyzen 5 7600XRyzen 9 7900XRyzen 7 7700XRyzen 9 7900X3DRyzen 9 7950X1.0352.073.1054.145.175SE +/- 0.12, N = 15SE +/- 0.03, N = 13SE +/- 0.03, N = 7SE +/- 0.04, N = 12SE +/- 0.03, N = 4SE +/- 0.30, N = 34.601.784.121.874.374.46MIN: 3.38 / MAX: 5.99MIN: 1.61 / MAX: 2.44MIN: 3.92 / MAX: 4.44MIN: 1.67 / MAX: 2.3MIN: 4.24 / MAX: 4.67MIN: 3.87 / MAX: 7.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

Row Count: 1000000 - Partitions: 100

Ryzen 9 7950X: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

Ryzen 9 7900X3D: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

Ryzen 7 7700X: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

Ryzen 9 7900X: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

Ryzen 5 7600X: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

Ryzen 9 7950X3D: The test run did not produce a result. E: _pickle.PicklingError: Could not serialize object: IndexError: tuple index out of range

268 Results Shown

LULESH
OpenVINO
oneDNN
Stress-NG
NCNN
OSPRay Studio:
  1 - 1080p - 32 - Path Tracer
  3 - 1080p - 32 - Path Tracer
ASKAP
OSPRay Studio:
  3 - 1080p - 1 - Path Tracer
  1 - 1080p - 16 - Path Tracer
  1 - 1080p - 1 - Path Tracer
  3 - 1080p - 16 - Path Tracer
OpenVINO
Stress-NG
ACES DGEMM
OpenVINO
Stress-NG:
  CPU Stress
  Vector Math
OpenVINO
NCNN
OpenSSL:
  SHA256
  SHA512
Stress-NG
OpenVINO
OpenSSL
John The Ripper:
  bcrypt
  Blowfish
Stress-NG
7-Zip Compression
RocksDB
OpenSSL
OpenVINO
Blender
John The Ripper
OSPRay
Blender:
  Pabellon Barcelona - CPU-Only
  Fishy Cat - CPU-Only
John The Ripper
OpenSSL
OSPRay
NCNN
Chaos Group V-RAY
OpenSSL
OSPRay
Stargate Digital Audio Workstation
OpenSSL:
  AES-128-GCM
  RSA4096
OSPRay
OpenVINO
Stockfish
Embree
OSPRay
NAMD
Embree
oneDNN
OpenVINO
oneDNN
Stargate Digital Audio Workstation
oneDNN
OpenVINO
CloverLeaf
oneDNN
Stargate Digital Audio Workstation
OpenVINO
Embree:
  Pathtracer - Asian Dragon
  Pathtracer - Asian Dragon Obj
OpenVINO
Stargate Digital Audio Workstation
Timed Linux Kernel Compilation
BRL-CAD
oneDNN
Embree
oneDNN
Embree
uvg266
ASKAP
x264
nginx
oneDNN
NCNN
Timed LLVM Compilation
OpenVKL
NCNN
uvg266
nginx
GROMACS
uvg266
nginx:
  1000
  500
Timed Node.js Compilation
Timed Godot Game Engine Compilation
Stress-NG
OpenFOAM
Pennant
Timed LLVM Compilation
OpenVINO
Timed FFmpeg Compilation
John The Ripper
OpenCV
Timed Linux Kernel Compilation
SPECFEM3D
ASKAP
Build2
7-Zip Compression
x264
Darktable
RocksDB
ASKAP
Pennant
NCNN
SPECFEM3D
x265
VVenC
SVT-AV1
Zstd Compression:
  8, Long Mode - Compression Speed
  8 - Compression Speed
Apache HTTP Server
Darktable
SPECFEM3D
NCNN
SVT-AV1
SPECFEM3D
GPAW
SPECFEM3D
OSPRay
VVenC
Memcached
VVenC
Memcached
Apache HTTP Server
SVT-AV1
Zstd Compression
RocksDB
Xcompact3d Incompact3d
SVT-AV1
Darktable
Memcached
ASKAP
Memcached
NCNN
OpenFOAM
Memcached
OpenFOAM
dav1d
ASKAP
x265
OpenFOAM
VVenC
OpenVINO
GIMP
Xcompact3d Incompact3d
VP9 libvpx Encoding
ASKAP
OpenVINO
OpenCV
OpenVINO
ClickHouse
Darktable
RocksDB
ClickHouse
Selenium
NCNN
OpenVINO:
  Weld Porosity Detection FP16 - CPU
  Face Detection FP16 - CPU
  Person Detection FP16 - CPU
NCNN
VP9 libvpx Encoding
OpenVINO
ClickHouse
NCNN
Selenium
OpenVINO
GIMP
VP9 libvpx Encoding
Darmstadt Automotive Parallel Heterogeneous Suite
Zstd Compression
OpenVINO
Apache HTTP Server
VP9 libvpx Encoding
Apache HTTP Server
Google Draco
dav1d
LeelaChessZero
ONNX Runtime
OpenCV
Zstd Compression
NCNN:
  CPU - yolov4-tiny
  CPU - alexnet
  CPU - resnet18
FFmpeg:
  libx265 - Upload:
    FPS
    Seconds
LeelaChessZero
NCNN
FFmpeg:
  libx265 - Platform:
    FPS
    Seconds
  libx265 - Video On Demand:
    Seconds
    FPS
GIMP
OpenVINO
OpenCV
dav1d
simdjson
OpenCV
Crafty
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
Google Draco
Selenium
FFmpeg:
  libx265 - Live:
    Seconds
    FPS
OpenCV
simdjson
GIMP
simdjson
NCNN
Selenium
PyBench
Zstd Compression
Selenium
dav1d
simdjson
Selenium
Darmstadt Automotive Parallel Heterogeneous Suite
simdjson
Zstd Compression
FFmpeg:
  libx264 - Live:
    Seconds
    FPS
Darmstadt Automotive Parallel Heterogeneous Suite
FFmpeg:
  libx264 - Platform:
    Seconds
    FPS
  libx264 - Video On Demand:
    Seconds
    FPS
  libx264 - Upload:
    FPS
    Seconds
Selenium:
  WASM imageConvolute - Firefox
  Speedometer - Firefox
  WASM collisionDetection - Firefox
  Speedometer - Google Chrome
WebP Image Encode
Selenium
PHPBench
WebP Image Encode
Numpy Benchmark
GNU Octave Benchmark
WebP Image Encode
Zstd Compression:
  12 - Decompression Speed
  8 - Decompression Speed
  8, Long Mode - Decompression Speed
OpenCV:
  DNN - Deep Neural Network
  Object Detection
Selenium
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
NCNN