AMD Ryzen 9 5950X Linux 5.11 Schedutil vs. Performance

Benchmarks by Michael Larabel. Linux 5.11 Git with freq invariance patch. Comparing CPUFreq schedutil and performance governor in various benchmarks.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2101255-PTS-RYZEN95916
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 5 Tests
Bioinformatics 3 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
Web Browsers 1 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 23 Tests
Compression Tests 5 Tests
CPU Massive 43 Tests
Creator Workloads 36 Tests
Cryptography 4 Tests
Desktop Graphics 4 Tests
Encoding 11 Tests
Fortran Tests 6 Tests
Game Development 2 Tests
HPC - High Performance Computing 27 Tests
Imaging 6 Tests
Java 2 Tests
Linear Algebra 2 Tests
Machine Learning 10 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 7 Tests
Multi-Core 48 Tests
NVIDIA GPU Compute 8 Tests
OCR 2 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 10 Tests
Productivity 2 Tests
Programmer / Developer System Benchmarks 10 Tests
Python Tests 9 Tests
Raytracing 4 Tests
Renderers 11 Tests
Rust Tests 3 Tests
Scientific Computing 14 Tests
Server CPU Tests 27 Tests
Single-Threaded 7 Tests
Speech 2 Tests
Telephony 2 Tests
Video Encoding 10 Tests
Common Workstation Benchmarks 6 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
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
CPUFreq Schedutil
January 21 2021
  16 Hours, 8 Minutes
CPUFreq Performance
January 24 2021
  11 Hours, 11 Minutes
Invert Hiding All Results Option
  13 Hours, 40 Minutes
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):

CPUFreq Schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

CPUFreq Performance

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3202 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.10, Kernel: 5.11.0-rc4-max-boost-inv-patch (x86_64) 20210121, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 21.0.0-devel (git-f01bca8 2021-01-08 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.164, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AMD Ryzen 9 5950X Linux 5.11 Schedutil vs. PerformanceOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3202 BIOS)AMD Starship/Matisse32GB2000GB Corsair Force MP600 + 2000GBAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz)AMD Navi 10 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.105.11.0-rc4-max-boost-inv-patch (x86_64) 20210121GNOME Shell 3.38.1X Server 1.20.9amdgpu 19.1.04.6 Mesa 21.0.0-devel (git-f01bca8 2021-01-08 groovy-oibaf-ppa) (LLVM 11.0.1)1.2.164GCC 10.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionAMD Ryzen 9 5950X Linux 5.11 Schedutil Vs. Performance BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 - CPUFreq Schedutil: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009- CPUFreq Performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009 - OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)- Python 3.8.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - CPUFreq Performance: GLAMOR

CPUFreq Schedutil vs. CPUFreq Performance ComparisonPhoronix Test SuiteBaseline+13.3%+13.3%+26.6%+26.6%+39.9%+39.9%+53.2%+53.2%53.3%52.7%37.6%11.8%11.3%10.9%9.8%9.7%9.5%8.5%7%6.9%6.7%6.5%5.6%4.6%4.4%4.4%4.3%4%3.8%3.5%3.4%3.4%3.3%3.3%3.3%3.3%3.3%3.2%3%3%2.7%2.7%2.6%2.6%2.3%2.2%2.2%2.1%2.1%2.1%TradebeansH.2.H.T.N.DC.1.1.bSpeed 6 RealtimeStyleBench - FirefoxCPUJetstream 2 - FirefoxI.M.D.SFayalite-FIST DataPSPDFKit WASM - Google ChromeSpeed 8 RealtimeJetstream 2 - Google ChromeblosclzARES-6 - Google ChromeSpeedometer - Google ChromeARES-6 - Firefox3840 x 2160 - Fullscreen - OpenGL 3.3 - Default - MulteasymapBLASR.N.N.T - f32 - CPUSqueezeNetV1.0EigenCPU Cache3.7%rotateStatic OMP Speedup3.4%Wavelet Volume - 3840 x 2160Wavelet Volume - 3840 x 2160SP.Bresizeauto-levelsCPU - alexnetIP Shapes 3D - f32 - CPUKraken - Google Chromeinception-v3R.N.N.I - f32 - CPUunsharp-maskS.F.P.RLU.CNo - Inference - VGG16 - CPUIP Shapes 1D - f32 - CPUCPU - resnet50Total Time2.2%BT.CNo - Inference - ResNet 50 - CPUCPU - yolov4-tinyD.I.S2%DaCapo BenchmarkFFmpegdav1dAOM AV1SeleniumDeepSpeechSeleniumRenaissanceCP2K Molecular DynamicsSeleniumAOM AV1SeleniumC-BloscSeleniumSeleniumSeleniumDDraceNetworkLeelaChessZerooneDNNMobile Neural NetworkLeelaChessZeroStress-NGGIMPCLOMPParaViewParaViewNAS Parallel BenchmarksGIMPGIMPNCNNoneDNNSeleniumNode.js V8 Web Tooling BenchmarkMobile Neural NetworkoneDNNGIMPACES DGEMMNAS Parallel BenchmarksPlaidMLoneDNNNCNNStockfishNAS Parallel BenchmarksPlaidMLNCNNAI Benchmark AlphaCPUFreq SchedutilCPUFreq Performance

AMD Ryzen 9 5950X Linux 5.11 Schedutil vs. Performancedacapobench: Tradebeansffmpeg: H.264 HD To NTSC DVdav1d: Chimera 1080p 10-bitaom-av1: Speed 6 Realtimeselenium: StyleBench - Firefoxdeepspeech: CPUselenium: Jetstream 2 - Firefoxcp2k: Fayalite-FIST Dataselenium: PSPDFKit WASM - Google Chromeaom-av1: Speed 8 Realtimeselenium: Jetstream 2 - Google Chromeblosc: blosclzselenium: ARES-6 - Google Chromeselenium: Speedometer - Google Chromeselenium: ARES-6 - Firefoxddnet: 3840 x 2160 - Fullscreen - OpenGL 3.3 - Default - Multeasymaplczero: BLASonednn: Recurrent Neural Network Training - f32 - CPUmnn: SqueezeNetV1.0lczero: Eigenstress-ng: CPU Cachegimp: rotateclomp: Static OMP Speedupparaview: Wavelet Volume - 3840 x 2160paraview: Wavelet Volume - 3840 x 2160npb: SP.Bgimp: resizegimp: auto-levelsncnn: CPU - alexnetonednn: IP Shapes 3D - f32 - CPUselenium: Kraken - Google Chromenode-web-tooling: mnn: inception-v3onednn: Recurrent Neural Network Inference - f32 - CPUgimp: unsharp-maskmt-dgemm: Sustained Floating-Point Ratenpb: LU.Cplaidml: No - Inference - VGG16 - CPUonednn: IP Shapes 1D - f32 - CPUncnn: CPU - resnet50stockfish: Total Timenpb: BT.Cplaidml: No - Inference - ResNet 50 - CPUncnn: CPU - yolov4-tinyai-benchmark: Device Inference Scoredacapobench: Jythonkripke: npb: CG.Cyquake2: Software CPU - 3840 x 2160tnn: CPU - SqueezeNet v1.1svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pncnn: CPU - vgg16rav1e: 5askap: tConvolve OpenMP - Griddingbuild-linux-kernel: Time To Compileai-benchmark: Device AI Scoreswet: Averagencnn: CPU - googlenetmafft: Multiple Sequence Alignment - LSU RNArust-mandel: Time To Complete Serial/Parallel Mandelbrotrenaissance: Akka Unbalanced Cobwebbed Treeaskap: tConvolve OpenMP - Degriddingsvt-vp9: Visual Quality Optimized - Bosphorus 1080prav1e: 6selenium: PSPDFKit WASM - Firefoxtesseract-ocr: Time To OCR 7 Imagesncnn: CPU - resnet18stress-ng: CPU Stressrenaissance: Twitter HTTP Requestscpuminer-opt: Garlicoinospray: Magnetic Reconnection - SciVisselenium: StyleBench - Google Chromewebp: Quality 100, Losslessgegl: Scalerenaissance: Apache Spark ALSai-benchmark: Device Training Scorenpb: MG.Cselenium: WASM imageConvolute - Firefoxcompress-lz4: 3 - Decompression Speeddav1d: Chimera 1080pembree: Pathtracer ISPC - Asian Dragonnpb: IS.Dplaidml: No - Inference - VGG19 - CPUxonotic: 3840 x 2160 - Ultimateddnet: 3840 x 2160 - Fullscreen - OpenGL 2.0 - Default - Multeasymapncnn: CPU - blazefacecompress-zstd: 3ncnn: CPU - mnasnetcloverleaf: Lagrangian-Eulerian Hydrodynamicscompress-lz4: 9 - Decompression Speedx264: H.264 Video Encodingselenium: WASM collisionDetection - Firefoxneatbench: CPUsvt-av1: Enc Mode 4 - 1080pncnn: CPU - shufflenet-v2avifenc: 8rav1e: 10namd: ATPase Simulation - 327,506 Atomsnpb: FT.Cbuild-gdb: Time To Compilencnn: CPU - squeezenet_ssdselenium: Speedometer - Firefoxffte: N=256, 3D Complex FFT Routineembree: Pathtracer - Asian Dragoncompress-lz4: 9 - Compression Speedradiance: SMP Parallelgit: Time To Complete Common Git Commandsdav1d: Summer Nature 4Kncnn: CPU - efficientnet-b0xonotic: 3840 x 2160 - Highxonotic: 3840 x 2160 - Ultrahimeno: Poisson Pressure Solverselenium: Kraken - Firefoxncnn: CPU - mobilenetaskap: tConvolve MT - Degriddingasmfish: 1024 Hash Memory, 26 Depthonednn: Convolution Batch Shapes Auto - f32 - CPUincompact3d: Cylindergputest: Plot3D - 3840 x 2160 - Fullscreenappleseed: Emilyxonotic: 3840 x 2160 - Lowgegl: Color Enhancesvt-av1: Enc Mode 8 - 1080ptesseract: 1920 x 1080embree: Pathtracer - Crowngputest: Triangle - 3840 x 2160 - Fullscreenselenium: WASM collisionDetection - Google Chromenpb: EP.Ccompress-7zip: Compress Speed Testxsbench: avifenc: 10ospray: NASA Streamlines - Path Traceramg: dolfyn: Computational Fluid Dynamicsdav1d: Summer Nature 1080pcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9blake2: ttsiod-renderer: Phong Rendering With Soft-Shadow Mappinggpaw: Carbon Nanotubecpuminer-opt: x25xaobench: 2048 x 2048 - Total Timegegl: Rotate 90 Degreesfinancebench: Repo OpenMPospray: San Miguel - Path Tracertnn: CPU - MobileNet v2cpuminer-opt: Magiocrmypdf: Processing 60 Page PDF Documentaircrack-ng: gromacs: Water Benchmarkprimesieve: 1e12 Prime Number Generationyquake2: OpenGL 3.x - 3840 x 2160rav1e: 1build-godot: Time To Compilewarsow: 1920 x 1080warsow: 3840 x 2160onednn: Deconvolution Batch shapes_1d - f32 - CPUaskap: tConvolve MT - Griddingunigine-super: 1920 x 1080 - Fullscreen - Low - OpenGLrnnoise: tachyon: Total Timecoremark: CoreMark Size 666 - Iterations Per Secondencode-flac: WAV To FLACbuild2: Time To Compileindigobench: CPU - Bedroomfinancebench: Bonds OpenMPtensorflow-lite: NASNet Mobilencnn: CPU-v2-v2 - mobilenet-v2hpcg: appleseed: Material Testerx265: Bosphorus 4Kembree: Pathtracer ISPC - Crownonednn: Deconvolution Batch shapes_3d - f32 - CPUgputest: Furmark - 3840 x 2160 - Fullscreenrust-prime: Prime Number Test To 200,000,000ospray: XFrog Forest - SciVisv-ray: CPUmrbayes: Primate Phylogeny Analysisindigobench: CPU - Supercarkvazaar: Bosphorus 4K - Ultra Fasthugin: Panorama Photo Assistant + Stitching Timetensorflow-lite: Inception ResNet V2vkmark: 3840 x 2160john-the-ripper: MD5john-the-ripper: Blowfishgputest: Pixmark Volplosion - 3840 x 2160 - Fullscreencrafty: Elapsed Timeyafaray: Total Time For Sample Scenetensorflow-lite: Mobilenet Quantstress-ng: Vector Mathsysbench: CPUc-ray: Total Time - 4K, 16 Rays Per Pixeltensorflow-lite: Inception V4selenium: WASM imageConvolute - Google Chromecompress-lz4: 3 - Compression Speedwebp: Quality 100, Lossless, Highest Compressiongputest: GiMark - 3840 x 2160 - Fullscreensmallpt: Global Illumination Renderer; 128 Samplesparaview: Wavelet Contour - 3840 x 2160paraview: Wavelet Contour - 3840 x 2160glmark2: 3840 x 2160tesseract: 3840 x 2160ncnn: CPU - regnety_400mgputest: TessMark - 3840 x 2160 - Fullscreensysbench: Memorytensorflow-lite: SqueezeNetstress-ng: Cryptolibraw: Post-Processing Benchmarktensorflow-lite: Mobilenet Floatastcenc: Exhaustivegputest: Pixmark Piano - 3840 x 2160 - Fullscreenunigine-super: 3840 x 2160 - Fullscreen - Low - OpenGLncnn: CPU-v3-v3 - mobilenet-v3kvazaar: Bosphorus 4K - Very Fastospray: XFrog Forest - Path Tracerospray: NASA Streamlines - SciVisospray: San Miguel - SciViscompress-zstd: 19renaissance: In-Memory Database ShootoutCPUFreq SchedutilCPUFreq Performance34606.453135.6230.5911561.7693791.873888.218306157.52196.47614457.314.4717944.80463.173902657.205.28539238.128.45421.33940.779246.307646.915.4349.54211.378.40829555.215.2331.5581686.6312.1229.41530427470.5020.923.8922725.454375589723612.8311.4621.7215442948739340706901.2448.9209.487228.6760.141.6313430.6245.9022743111358947313.247.41331.6099117.3594204.55222.172.191282618.82414.7612206.421890.0315232.8521.7455.212.9574.5201395.64511999812.7324.213130.5900.4225.6582650.1417.38376.9448431305.921.834798.34.00136.2413094.6208.87302.932.66.0944.444.2775.0601.0874512056.3962.61914.7012534673.87782510724.809668.39141.30138.028238.795.40540.7442902472.03541875309.464212903.212.201884.495999196216.9879182.89617968923190.538231675.272359240.86251.966691.123924.2868424552253.01801902.479564031416664.0948.2620923753313.051924.6422.9914.411037.51326.376623.1927.36529.50927738.2864582.47214.925867.3912.47374981.0181.26011.149987.00.55579.566957.9432.72.43083915.039241.415.33844.4373813873.2775436.33281.5714.14239803.7825521039964.464.24824112.25249928.0723.84763.5406946205.1825.493250862.9918.67453.4034.076121720064022170003825620911135673866.57968077.2172877.3290585.224430.865135283324.673770.1327.173108704.924197.322056.3222873426.412017.741959715419966.364595054.44838.1854.1162792.5100.6284696.44.1629.352.944030.0143.42850.39722574.227186.6034.2112855.68045100.843811.109282261.53210.00115423.413.5918942.85483.434072547.965.08240736.778.17020.64074.540254.667899.905.2619.23911.018.14337537.915.6930.6481642.3211.8059.65900128180.6521.403.8069524.904281882924115.4211.7021.2815132892725310257034.5449.8213.338232.7859.081.6603371.4245.1152696109488152413.027.29332.1229263.4724271.73225.682.225278318.53814.5412390.161917.9765310.1622.0656.013.1444.4581376.54211839940.5323.913288.2911.1125.3609642.7417.58381.1593016309.341.814850.63.96134.9513219.4210.86300.132.96.1504.404.2395.1051.0782012156.3962.10614.5812634946.48399339325.003567.86140.20637.737236.985.36544.6134730475.23731315273.764576897.212.121896.756037980317.0959181.76532068498189.417153671.339594041.09352.251694.835524.1627426719251.73421893.049516831571434.0748.2221025426712.988929.0523.0964.431042.10325.013620.6027.25229.63127852.0031252.46215.798863.9012.42375278.7991.26511.108990.60.55779.286961.1431.32.42349917.729242.115.38144.3161816060.5729736.34981.3694.13239899.1575521042354.474.25755112.49316628.0123.79673.5336446115.1725.503245162.8828.65953.3134.022121529364122203333831120941137264766.67167985.1173101.0090701.132230.903135133024.646370.2027.149108614.928197.162054.6652875426.691917.751960815428518.924695103.94840.5054.0962771.6100.5984696.44.1629.352.944030.0143.42597.432OpenBenchmarking.org

DDraceNetwork

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame TimeCPUFreq SchedutilCPUFreq Performance3691215Min: 2 / Avg: 2.36 / Max: 8.11Min: 2 / Avg: 2.08 / Max: 9.221. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 2.0 - Zoom: Default - Demo: Multeasymap - Total Frame TimeCPUFreq SchedutilCPUFreq Performance3691215Min: 2.1 / Avg: 3.35 / Max: 6.48Min: 2.39 / Avg: 3.2 / Max: 4.521. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansCPUFreq SchedutilCPUFreq Performance7001400210028003500SE +/- 42.31, N = 4SE +/- 2.17, N = 434602257
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansCPUFreq SchedutilCPUFreq Performance6001200180024003000Min: 3388 / Avg: 3460 / Max: 3582Min: 2251 / Avg: 2257.25 / Max: 2261

FFmpeg

This test uses FFmpeg for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DVCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.062, N = 6SE +/- 0.037, N = 36.4534.2271. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lasound -lSDL2 -lsndio -pthread -lbz2 -llzma -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DVCPUFreq SchedutilCPUFreq Performance3691215Min: 6.2 / Avg: 6.45 / Max: 6.59Min: 4.15 / Avg: 4.23 / Max: 4.271. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lasound -lSDL2 -lsndio -pthread -lbz2 -llzma -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Chimera 1080p 10-bitCPUFreq SchedutilCPUFreq Performance4080120160200SE +/- 0.53, N = 3SE +/- 0.10, N = 3135.62186.60MIN: 94.6 / MAX: 335.55MIN: 120.55 / MAX: 370.281. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Chimera 1080p 10-bitCPUFreq SchedutilCPUFreq Performance306090120150Min: 134.57 / Avg: 135.62 / Max: 136.18Min: 186.41 / Avg: 186.6 / Max: 186.751. (CC) gcc options: -pthread

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 RealtimeCPUFreq SchedutilCPUFreq Performance816243240SE +/- 0.29, N = 15SE +/- 0.25, N = 330.5934.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 RealtimeCPUFreq SchedutilCPUFreq Performance714212835Min: 28.67 / Avg: 30.59 / Max: 31.98Min: 33.78 / Avg: 34.21 / Max: 34.641. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance306090120150SE +/- 1.76, N = 31151281. firefox 84.0.2
OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance20406080100Min: 125 / Avg: 127.67 / Max: 1311. firefox 84.0.2

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUCPUFreq SchedutilCPUFreq Performance1428425670SE +/- 0.46, N = 3SE +/- 0.30, N = 361.7755.68
OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUCPUFreq SchedutilCPUFreq Performance1224364860Min: 61.3 / Avg: 61.77 / Max: 62.69Min: 55.1 / Avg: 55.68 / Max: 56.05

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance20406080100SE +/- 0.99, N = 3SE +/- 1.02, N = 391.87100.841. firefox 84.0.2
OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance20406080100Min: 90.33 / Avg: 91.87 / Max: 93.72Min: 99.1 / Avg: 100.84 / Max: 102.631. firefox 84.0.2

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.1Fayalite-FIST DataCPUFreq SchedutilCPUFreq Performance2004006008001000888.22811.11

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance7001400210028003500SE +/- 6.69, N = 3SE +/- 3.61, N = 3306128221. chrome 88.0.4324.96
OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance5001000150020002500Min: 3049 / Avg: 3061.33 / Max: 3072Min: 2815 / Avg: 2822 / Max: 28271. chrome 88.0.4324.96

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 RealtimeCPUFreq SchedutilCPUFreq Performance1428425670SE +/- 0.37, N = 3SE +/- 0.60, N = 357.5261.531. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 RealtimeCPUFreq SchedutilCPUFreq Performance1224364860Min: 57.08 / Avg: 57.52 / Max: 58.25Min: 60.51 / Avg: 61.53 / Max: 62.591. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 0.82, N = 3SE +/- 1.04, N = 3196.48210.001. chrome 88.0.4324.96
OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance4080120160200Min: 195.37 / Avg: 196.48 / Max: 198.09Min: 208.23 / Avg: 210 / Max: 211.831. chrome 88.0.4324.96

C-Blosc

A simple, compressed, fast and persistent data store library for C. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KSE +/- 95.24, N = 3SE +/- 19.42, N = 314457.315423.41. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KMin: 14268.6 / Avg: 14457.33 / Max: 14574Min: 15384.9 / Avg: 15423.4 / Max: 15447.11. (CXX) g++ options: -rdynamic

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.09, N = 3SE +/- 0.02, N = 314.4713.591. chrome 88.0.4324.96
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance48121620Min: 14.36 / Avg: 14.47 / Max: 14.64Min: 13.55 / Avg: 13.59 / Max: 13.621. chrome 88.0.4324.96

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance4080120160200SE +/- 0.67, N = 31791891. chrome 88.0.4324.96
OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance306090120150Min: 178 / Avg: 179.33 / Max: 1801. chrome 88.0.4324.96

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance1020304050SE +/- 0.37, N = 3SE +/- 0.27, N = 344.8042.851. firefox 84.0.2
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance918273645Min: 44.31 / Avg: 44.8 / Max: 45.52Min: 42.5 / Avg: 42.85 / Max: 43.381. firefox 84.0.2

DDraceNetwork

This is a test of DDraceNetwork, an open-source cooperative platformer. OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: MulteasymapCPUFreq SchedutilCPUFreq Performance100200300400500SE +/- 4.61, N = 15SE +/- 1.35, N = 3463.17483.43MIN: 194.67 / MAX: 499.75MIN: 230.1 / MAX: 499.751. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: MulteasymapCPUFreq SchedutilCPUFreq Performance90180270360450Min: 424.73 / Avg: 463.17 / Max: 484.16Min: 481.82 / Avg: 483.43 / Max: 486.121. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

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 0.26Backend: BLASCPUFreq SchedutilCPUFreq Performance90180270360450SE +/- 3.38, N = 3SE +/- 3.79, N = 33904071. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASCPUFreq SchedutilCPUFreq Performance70140210280350Min: 383 / Avg: 389.67 / Max: 394Min: 400 / Avg: 407 / Max: 4131. (CXX) g++ options: -flto -pthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance6001200180024003000SE +/- 30.62, N = 3SE +/- 25.11, N = 32657.202547.96MIN: 2608.63MIN: 2500.161. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance5001000150020002500Min: 2618.82 / Avg: 2657.2 / Max: 2717.72Min: 2509.29 / Avg: 2547.96 / Max: 2595.051. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: SqueezeNetV1.0CPUFreq SchedutilCPUFreq Performance1.18912.37823.56734.75645.9455SE +/- 0.072, N = 3SE +/- 0.064, N = 35.2855.082MIN: 5.07 / MAX: 8.3MIN: 4.88 / MAX: 6.431. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: SqueezeNetV1.0CPUFreq SchedutilCPUFreq Performance246810Min: 5.15 / Avg: 5.28 / Max: 5.38Min: 5 / Avg: 5.08 / Max: 5.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

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 0.26Backend: EigenCPUFreq SchedutilCPUFreq Performance90180270360450SE +/- 3.79, N = 3SE +/- 2.85, N = 33924071. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenCPUFreq SchedutilCPUFreq Performance70140210280350Min: 386 / Avg: 392 / Max: 399Min: 404 / Avg: 407.33 / Max: 4131. (CXX) g++ options: -flto -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CacheCPUFreq SchedutilCPUFreq Performance918273645SE +/- 0.35, N = 15SE +/- 0.31, N = 1538.1236.771. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CacheCPUFreq SchedutilCPUFreq Performance816243240Min: 35.23 / Avg: 38.12 / Max: 40.96Min: 35.32 / Avg: 36.77 / Max: 38.621. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 2.10.18Test: rotateCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.012, N = 3SE +/- 0.036, N = 38.4548.170
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: rotateCPUFreq SchedutilCPUFreq Performance3691215Min: 8.44 / Avg: 8.45 / Max: 8.48Min: 8.1 / Avg: 8.17 / Max: 8.23

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupCPUFreq SchedutilCPUFreq Performance510152025SE +/- 0.06, N = 3SE +/- 0.16, N = 921.320.61. (CC) gcc options: -fopenmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupCPUFreq SchedutilCPUFreq Performance510152025Min: 21.2 / Avg: 21.3 / Max: 21.4Min: 19.5 / Avg: 20.63 / Max: 21.11. (CC) gcc options: -fopenmp -O3 -lm

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance9001800270036004500SE +/- 31.91, N = 3SE +/- 8.93, N = 33940.784074.54
OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance7001400210028003500Min: 3884.57 / Avg: 3940.78 / Max: 3995.04Min: 4056.76 / Avg: 4074.54 / Max: 4084.83

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance60120180240300SE +/- 1.99, N = 3SE +/- 0.56, N = 3246.30254.66
OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance50100150200250Min: 242.79 / Avg: 246.3 / Max: 249.69Min: 253.55 / Avg: 254.66 / Max: 255.3

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KSE +/- 1.81, N = 3SE +/- 10.19, N = 37646.917899.901. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BCPUFreq SchedutilCPUFreq Performance14002800420056007000Min: 7643.4 / Avg: 7646.91 / Max: 7649.45Min: 7887.55 / Avg: 7899.9 / Max: 7920.121. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

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 2.10.18Test: resizeCPUFreq SchedutilCPUFreq Performance1.22272.44543.66814.89086.1135SE +/- 0.060, N = 3SE +/- 0.059, N = 35.4345.261
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: resizeCPUFreq SchedutilCPUFreq Performance246810Min: 5.36 / Avg: 5.43 / Max: 5.55Min: 5.19 / Avg: 5.26 / Max: 5.38

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: auto-levelsCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.049, N = 3SE +/- 0.063, N = 39.5429.239
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: auto-levelsCPUFreq SchedutilCPUFreq Performance3691215Min: 9.49 / Avg: 9.54 / Max: 9.64Min: 9.12 / Avg: 9.24 / Max: 9.33

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 20201218Target: CPU - Model: alexnetCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.11, N = 14SE +/- 0.01, N = 311.3711.01MIN: 11.05 / MAX: 12.62MIN: 10.9 / MAX: 11.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetCPUFreq SchedutilCPUFreq Performance3691215Min: 11.17 / Avg: 11.37 / Max: 12.46Min: 10.99 / Avg: 11.01 / Max: 11.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.05229, N = 3SE +/- 0.08822, N = 38.408298.14337MIN: 7.95MIN: 7.771. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance3691215Min: 8.3 / Avg: 8.41 / Max: 8.46Min: 8 / Avg: 8.14 / Max: 8.311. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance120240360480600SE +/- 3.55, N = 3SE +/- 2.34, N = 3555.2537.91. chrome 88.0.4324.96
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance100200300400500Min: 548.2 / Avg: 555.2 / Max: 559.7Min: 533.4 / Avg: 537.93 / Max: 541.21. chrome 88.0.4324.96

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.11, N = 3SE +/- 0.03, N = 315.2315.691. Nodejs v12.18.2
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkCPUFreq SchedutilCPUFreq Performance48121620Min: 15.01 / Avg: 15.23 / Max: 15.36Min: 15.66 / Avg: 15.69 / Max: 15.741. Nodejs v12.18.2

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: inception-v3CPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.31, N = 3SE +/- 0.38, N = 331.5630.65MIN: 30.24 / MAX: 40.01MIN: 29.11 / MAX: 57.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: inception-v3CPUFreq SchedutilCPUFreq Performance714212835Min: 30.98 / Avg: 31.56 / Max: 32.03Min: 29.96 / Avg: 30.65 / Max: 31.281. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 19.21, N = 15SE +/- 20.59, N = 31686.631642.32MIN: 1583.35MIN: 1607.811. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance30060090012001500Min: 1601.85 / Avg: 1686.63 / Max: 1789.51Min: 1617.31 / Avg: 1642.32 / Max: 1683.161. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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 2.10.18Test: unsharp-maskCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.04, N = 3SE +/- 0.03, N = 312.1211.81
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: unsharp-maskCPUFreq SchedutilCPUFreq Performance48121620Min: 12.06 / Avg: 12.12 / Max: 12.2Min: 11.77 / Avg: 11.81 / Max: 11.87

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 RateCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.091260, N = 15SE +/- 0.048345, N = 39.4153049.6590011. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateCPUFreq SchedutilCPUFreq Performance3691215Min: 8.63 / Avg: 9.42 / Max: 9.99Min: 9.57 / Avg: 9.66 / Max: 9.741. (CC) gcc options: -O3 -march=native -fopenmp

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CCPUFreq SchedutilCPUFreq Performance6K12K18K24K30KSE +/- 30.90, N = 3SE +/- 19.76, N = 327470.5028180.651. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CCPUFreq SchedutilCPUFreq Performance5K10K15K20K25KMin: 27408.86 / Avg: 27470.5 / Max: 27505.16Min: 28141.51 / Avg: 28180.65 / Max: 28204.951. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUCPUFreq SchedutilCPUFreq Performance510152025SE +/- 0.12, N = 3SE +/- 0.12, N = 320.9221.40
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUCPUFreq SchedutilCPUFreq Performance510152025Min: 20.76 / Avg: 20.92 / Max: 21.16Min: 21.16 / Avg: 21.4 / Max: 21.55

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance0.87581.75162.62743.50324.379SE +/- 0.00345, N = 3SE +/- 0.01973, N = 33.892273.80695MIN: 3.71MIN: 3.61. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance246810Min: 3.89 / Avg: 3.89 / Max: 3.9Min: 3.78 / Avg: 3.81 / Max: 3.851. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 20201218Target: CPU - Model: resnet50CPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.21, N = 14SE +/- 0.16, N = 325.4524.90MIN: 24.75 / MAX: 36.04MIN: 24.54 / MAX: 26.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50CPUFreq SchedutilCPUFreq Performance612182430Min: 25.01 / Avg: 25.45 / Max: 27.55Min: 24.72 / Avg: 24.9 / Max: 25.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total TimeCPUFreq SchedutilCPUFreq Performance9M18M27M36M45MSE +/- 311694.90, N = 3SE +/- 63424.87, N = 343755897428188291. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total TimeCPUFreq SchedutilCPUFreq Performance8M16M24M32M40MMin: 43404556 / Avg: 43755897 / Max: 44377528Min: 42725657 / Avg: 42818829.33 / Max: 429399631. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CCPUFreq SchedutilCPUFreq Performance5K10K15K20K25KSE +/- 15.09, N = 3SE +/- 21.18, N = 323612.8324115.421. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CCPUFreq SchedutilCPUFreq Performance4K8K12K16K20KMin: 23586.23 / Avg: 23612.83 / Max: 23638.47Min: 24094.01 / Avg: 24115.42 / Max: 24157.771. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.16, N = 3SE +/- 0.03, N = 311.4611.70
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUCPUFreq SchedutilCPUFreq Performance3691215Min: 11.14 / Avg: 11.46 / Max: 11.66Min: 11.65 / Avg: 11.7 / Max: 11.74

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 20201218Target: CPU - Model: yolov4-tinyCPUFreq SchedutilCPUFreq Performance510152025SE +/- 0.20, N = 14SE +/- 0.04, N = 321.7221.28MIN: 20.98 / MAX: 29.43MIN: 21 / MAX: 22.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyCPUFreq SchedutilCPUFreq Performance510152025Min: 21.26 / Avg: 21.72 / Max: 23.79Min: 21.23 / Avg: 21.28 / Max: 21.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreCPUFreq SchedutilCPUFreq Performance3006009001200150015441513

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonCPUFreq SchedutilCPUFreq Performance6001200180024003000SE +/- 11.29, N = 4SE +/- 22.28, N = 429482892
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonCPUFreq SchedutilCPUFreq Performance5001000150020002500Min: 2925 / Avg: 2947.75 / Max: 2976Min: 2853 / Avg: 2891.5 / Max: 2947

Kripke

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

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4CPUFreq SchedutilCPUFreq Performance16M32M48M64M80MSE +/- 451180.36, N = 3SE +/- 482772.60, N = 1473934070725310251. (CXX) g++ options: -O3 -fopenmp
OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4CPUFreq SchedutilCPUFreq Performance13M26M39M52M65MMin: 73134890 / Avg: 73934070 / Max: 74696530Min: 69364200 / Avg: 72531025 / Max: 758156301. (CXX) g++ options: -O3 -fopenmp

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CCPUFreq SchedutilCPUFreq Performance15003000450060007500SE +/- 33.82, N = 3SE +/- 18.96, N = 36901.247034.541. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CCPUFreq SchedutilCPUFreq Performance12002400360048006000Min: 6833.87 / Avg: 6901.24 / Max: 6940.16Min: 7009.07 / Avg: 7034.54 / Max: 7071.61. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance1122334455SE +/- 0.44, N = 3SE +/- 0.38, N = 348.949.81. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance1020304050Min: 48.1 / Avg: 48.93 / Max: 49.6Min: 49.1 / Avg: 49.8 / Max: 50.41. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1CPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 0.90, N = 3SE +/- 0.18, N = 3209.49213.34MIN: 207.52 / MAX: 210.75MIN: 212.91 / MAX: 213.841. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1CPUFreq SchedutilCPUFreq Performance4080120160200Min: 207.72 / Avg: 209.49 / Max: 210.65Min: 213.01 / Avg: 213.34 / Max: 213.611. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 2.00, N = 13SE +/- 2.12, N = 12228.67232.781. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pCPUFreq SchedutilCPUFreq Performance4080120160200Min: 204.85 / Avg: 228.67 / Max: 231.84Min: 209.57 / Avg: 232.78 / Max: 236.311. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 20201218Target: CPU - Model: vgg16CPUFreq SchedutilCPUFreq Performance1326395265SE +/- 0.03, N = 14SE +/- 0.03, N = 360.1459.08MIN: 58.9 / MAX: 140.56MIN: 58.07 / MAX: 60.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16CPUFreq SchedutilCPUFreq Performance1224364860Min: 59.96 / Avg: 60.14 / Max: 60.49Min: 59.03 / Avg: 59.08 / Max: 59.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5CPUFreq SchedutilCPUFreq Performance0.37350.7471.12051.4941.8675SE +/- 0.014, N = 3SE +/- 0.005, N = 31.6311.660
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5CPUFreq SchedutilCPUFreq Performance246810Min: 1.6 / Avg: 1.63 / Max: 1.65Min: 1.65 / Avg: 1.66 / Max: 1.67

ASKAP

This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - GriddingCPUFreq SchedutilCPUFreq Performance7001400210028003500SE +/- 36.96, N = 15SE +/- 43.22, N = 33430.623371.421. (CXX) g++ options: -lpthread
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - GriddingCPUFreq SchedutilCPUFreq Performance6001200180024003000Min: 3287.11 / Avg: 3430.62 / Max: 3750.08Min: 3328.2 / Avg: 3371.42 / Max: 3457.871. (CXX) g++ options: -lpthread

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileCPUFreq SchedutilCPUFreq Performance1020304050SE +/- 0.32, N = 3SE +/- 0.30, N = 345.9045.12
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileCPUFreq SchedutilCPUFreq Performance918273645Min: 45.55 / Avg: 45.9 / Max: 46.54Min: 44.51 / Avg: 45.11 / Max: 45.43

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreCPUFreq SchedutilCPUFreq Performance600120018002400300027432696

Swet

Swet is a synthetic CPU/RAM benchmark, includes multi-processor test cases. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16AverageCPUFreq SchedutilCPUFreq Performance200M400M600M800M1000MSE +/- 9522937.85, N = 3SE +/- 13144909.98, N = 3111358947310948815241. (CC) gcc options: -lm -lpthread -lcurses -lrt
OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16AverageCPUFreq SchedutilCPUFreq Performance200M400M600M800M1000MMin: 1098061760 / Avg: 1113589473.33 / Max: 1130904593Min: 1072523631 / Avg: 1094881524 / Max: 11180379261. (CC) gcc options: -lm -lpthread -lcurses -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 20201218Target: CPU - Model: googlenetCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.15, N = 14SE +/- 0.03, N = 313.2413.02MIN: 12.64 / MAX: 22.25MIN: 12.62 / MAX: 13.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetCPUFreq SchedutilCPUFreq Performance48121620Min: 12.97 / Avg: 13.24 / Max: 15.15Min: 12.96 / Avg: 13.02 / Max: 13.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNACPUFreq SchedutilCPUFreq Performance246810SE +/- 0.030, N = 3SE +/- 0.045, N = 37.4137.2931. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNACPUFreq SchedutilCPUFreq Performance3691215Min: 7.36 / Avg: 7.41 / Max: 7.47Min: 7.24 / Avg: 7.29 / Max: 7.381. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Rust Mandelbrot

This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.18, N = 3SE +/- 0.12, N = 331.6132.121. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotCPUFreq SchedutilCPUFreq Performance714212835Min: 31.4 / Avg: 31.61 / Max: 31.97Min: 31.88 / Avg: 32.12 / Max: 32.241. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KSE +/- 67.30, N = 11SE +/- 69.42, N = 59117.369263.47
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeCPUFreq SchedutilCPUFreq Performance16003200480064008000Min: 8566.07 / Avg: 9117.36 / Max: 9361.25Min: 9096.7 / Avg: 9263.47 / Max: 9519.7

ASKAP

This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - DegriddingCPUFreq SchedutilCPUFreq Performance9001800270036004500SE +/- 12.33, N = 15SE +/- 22.72, N = 34204.554271.731. (CXX) g++ options: -lpthread
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - DegriddingCPUFreq SchedutilCPUFreq Performance7001400210028003500Min: 4096.25 / Avg: 4204.55 / Max: 4294.45Min: 4226.29 / Avg: 4271.73 / Max: 4294.451. (CXX) g++ options: -lpthread

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 0.36, N = 3SE +/- 0.84, N = 3222.17225.681. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pCPUFreq SchedutilCPUFreq Performance4080120160200Min: 221.73 / Avg: 222.17 / Max: 222.88Min: 224.3 / Avg: 225.68 / Max: 227.191. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6CPUFreq SchedutilCPUFreq Performance0.50061.00121.50182.00242.503SE +/- 0.010, N = 3SE +/- 0.004, N = 32.1912.225
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6CPUFreq SchedutilCPUFreq Performance246810Min: 2.17 / Avg: 2.19 / Max: 2.2Min: 2.22 / Avg: 2.23 / Max: 2.23

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance6001200180024003000SE +/- 23.10, N = 3SE +/- 11.89, N = 3282627831. firefox 84.0.2
OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance5001000150020002500Min: 2786 / Avg: 2826.33 / Max: 2866Min: 2764 / Avg: 2783.33 / Max: 28051. firefox 84.0.2

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesCPUFreq SchedutilCPUFreq Performance510152025SE +/- 0.18, N = 15SE +/- 0.17, N = 318.8218.54
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesCPUFreq SchedutilCPUFreq Performance510152025Min: 18.27 / Avg: 18.82 / Max: 20.93Min: 18.2 / Avg: 18.54 / Max: 18.78

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 20201218Target: CPU - Model: resnet18CPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.08, N = 14SE +/- 0.00, N = 314.7614.54MIN: 14.51 / MAX: 16.44MIN: 14.44 / MAX: 15.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18CPUFreq SchedutilCPUFreq Performance48121620Min: 14.64 / Avg: 14.76 / Max: 15.71Min: 14.53 / Avg: 14.54 / Max: 14.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KSE +/- 90.40, N = 3SE +/- 126.71, N = 312206.4212390.161. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 12054.19 / Avg: 12206.42 / Max: 12367.01Min: 12156.71 / Avg: 12390.16 / Max: 12592.271. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Twitter HTTP RequestsCPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 14.57, N = 5SE +/- 15.72, N = 51890.031917.98
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Twitter HTTP RequestsCPUFreq SchedutilCPUFreq Performance30060090012001500Min: 1855.14 / Avg: 1890.03 / Max: 1924.55Min: 1874.08 / Avg: 1917.98 / Max: 1961.32

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: GarlicoinCPUFreq SchedutilCPUFreq Performance11002200330044005500SE +/- 33.18, N = 3SE +/- 1.61, N = 35232.855310.161. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: GarlicoinCPUFreq SchedutilCPUFreq Performance9001800270036004500Min: 5181.63 / Avg: 5232.85 / Max: 5294.99Min: 5308.42 / Avg: 5310.16 / Max: 5313.381. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity 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.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance510152025SE +/- 0.00, N = 3SE +/- 0.16, N = 321.7422.06MIN: 21.28 / MAX: 22.22MIN: 21.28 / MAX: 22.22
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance510152025Min: 21.74 / Avg: 21.74 / Max: 21.74Min: 21.74 / Avg: 22.06 / Max: 22.22

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance1326395265SE +/- 0.09, N = 3SE +/- 0.54, N = 355.256.01. chrome 88.0.4324.96
OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance1122334455Min: 55.1 / Avg: 55.23 / Max: 55.4Min: 55.2 / Avg: 55.97 / Max: 571. chrome 88.0.4324.96

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.09, N = 3SE +/- 0.00, N = 312.9613.141. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessCPUFreq SchedutilCPUFreq Performance48121620Min: 12.79 / Avg: 12.96 / Max: 13.09Min: 13.14 / Avg: 13.14 / Max: 13.151. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleCPUFreq SchedutilCPUFreq Performance1.0172.0343.0514.0685.085SE +/- 0.030, N = 13SE +/- 0.027, N = 34.5204.458
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleCPUFreq SchedutilCPUFreq Performance246810Min: 4.41 / Avg: 4.52 / Max: 4.86Min: 4.42 / Avg: 4.46 / Max: 4.51

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSCPUFreq SchedutilCPUFreq Performance30060090012001500SE +/- 12.63, N = 5SE +/- 8.37, N = 251395.651376.54
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSCPUFreq SchedutilCPUFreq Performance2004006008001000Min: 1357.29 / Avg: 1395.64 / Max: 1434.32Min: 1310.93 / Avg: 1376.54 / Max: 1495.88

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreCPUFreq SchedutilCPUFreq Performance3006009001200150011991183

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KSE +/- 2.42, N = 3SE +/- 2.93, N = 39812.739940.531. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 9808.31 / Avg: 9812.73 / Max: 9816.64Min: 9934.69 / Avg: 9940.53 / Max: 9943.921. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.06, N = 3SE +/- 0.07, N = 324.223.91. firefox 84.0.2
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance612182430Min: 24.1 / Avg: 24.2 / Max: 24.3Min: 23.8 / Avg: 23.93 / Max: 241. firefox 84.0.2

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KSE +/- 44.20, N = 5SE +/- 19.12, N = 413130.513288.21. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 13048.6 / Avg: 13130.52 / Max: 13282.7Min: 13234.1 / Avg: 13288.2 / Max: 13323.51. (CC) gcc 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 0.8.1Video Input: Chimera 1080pCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 0.21, N = 3SE +/- 1.15, N = 3900.42911.11MIN: 700.11 / MAX: 1100.45MIN: 710.88 / MAX: 1109.351. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Chimera 1080pCPUFreq SchedutilCPUFreq Performance160320480640800Min: 900.12 / Avg: 900.42 / Max: 900.83Min: 909.17 / Avg: 911.11 / Max: 913.151. (CC) gcc options: -pthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian DragonCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.14, N = 3SE +/- 0.04, N = 325.6625.36MIN: 25.3 / MAX: 26.13MIN: 25.16 / MAX: 25.7
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian DragonCPUFreq SchedutilCPUFreq Performance612182430Min: 25.41 / Avg: 25.66 / Max: 25.88Min: 25.27 / Avg: 25.36 / Max: 25.41

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DCPUFreq SchedutilCPUFreq Performance140280420560700SE +/- 2.15, N = 3SE +/- 1.97, N = 3650.14642.741. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DCPUFreq SchedutilCPUFreq Performance110220330440550Min: 645.87 / Avg: 650.14 / Max: 652.66Min: 638.87 / Avg: 642.74 / Max: 645.311. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.08, N = 3SE +/- 0.20, N = 317.3817.58
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUCPUFreq SchedutilCPUFreq Performance48121620Min: 17.28 / Avg: 17.38 / Max: 17.55Min: 17.18 / Avg: 17.58 / Max: 17.83

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimateCPUFreq SchedutilCPUFreq Performance80160240320400SE +/- 1.38, N = 3SE +/- 0.23, N = 3376.94381.16MIN: 63 / MAX: 622MIN: 64 / MAX: 628
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimateCPUFreq SchedutilCPUFreq Performance70140210280350Min: 374.41 / Avg: 376.94 / Max: 379.16Min: 380.7 / Avg: 381.16 / Max: 381.46

DDraceNetwork

This is a test of DDraceNetwork, an open-source cooperative platformer. OpenGL 3.3 is used for rendering, with fallbacks for older OpenGL versions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 2.0 - Zoom: Default - Demo: MulteasymapCPUFreq SchedutilCPUFreq Performance70140210280350SE +/- 2.92, N = 3SE +/- 2.40, N = 3305.92309.34MIN: 154.42 / MAX: 477.33MIN: 157.78 / MAX: 462.961. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 2.0 - Zoom: Default - Demo: MulteasymapCPUFreq SchedutilCPUFreq Performance60120180240300Min: 300.47 / Avg: 305.92 / Max: 310.48Min: 306.12 / Avg: 309.34 / Max: 314.031. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

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 20201218Target: CPU - Model: blazefaceCPUFreq SchedutilCPUFreq Performance0.41180.82361.23541.64722.059SE +/- 0.01, N = 14SE +/- 0.00, N = 31.831.81MIN: 1.79 / MAX: 2.15MIN: 1.79 / MAX: 1.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceCPUFreq SchedutilCPUFreq Performance246810Min: 1.81 / Avg: 1.83 / Max: 2.01Min: 1.81 / Avg: 1.81 / Max: 1.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3CPUFreq SchedutilCPUFreq Performance10002000300040005000SE +/- 14.80, N = 3SE +/- 11.81, N = 34798.34850.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3CPUFreq SchedutilCPUFreq Performance8001600240032004000Min: 4771.6 / Avg: 4798.33 / Max: 4822.7Min: 4828.3 / Avg: 4850.57 / Max: 4868.51. (CC) gcc options: -O3 -pthread -lz -llzma

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 20201218Target: CPU - Model: mnasnetCPUFreq SchedutilCPUFreq Performance0.91.82.73.64.5SE +/- 0.03, N = 14SE +/- 0.01, N = 34.003.96MIN: 3.83 / MAX: 5.25MIN: 3.83 / MAX: 4.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetCPUFreq SchedutilCPUFreq Performance246810Min: 3.94 / Avg: 4 / Max: 4.4Min: 3.95 / Avg: 3.96 / Max: 3.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 HydrodynamicsCPUFreq SchedutilCPUFreq Performance306090120150SE +/- 0.43, N = 3SE +/- 0.18, N = 3136.24134.951. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsCPUFreq SchedutilCPUFreq Performance306090120150Min: 135.4 / Avg: 136.24 / Max: 136.86Min: 134.61 / Avg: 134.95 / Max: 135.191. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KSE +/- 59.42, N = 3SE +/- 66.85, N = 313094.613219.41. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 13016.3 / Avg: 13094.63 / Max: 13211.2Min: 13122.9 / Avg: 13219.4 / Max: 13347.81. (CC) gcc options: -O3

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 1.52, N = 13SE +/- 1.26, N = 15208.87210.861. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingCPUFreq SchedutilCPUFreq Performance4080120160200Min: 191.08 / Avg: 208.87 / Max: 212.31Min: 193.92 / Avg: 210.86 / Max: 214.441. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance70140210280350SE +/- 1.12, N = 3SE +/- 1.09, N = 3302.9300.11. firefox 84.0.2
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance50100150200250Min: 300.7 / Avg: 302.93 / Max: 304.1Min: 298 / Avg: 300.07 / Max: 301.71. firefox 84.0.2

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUCPUFreq SchedutilCPUFreq Performance816243240SE +/- 0.15, N = 3SE +/- 0.15, N = 332.632.9
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUCPUFreq SchedutilCPUFreq Performance714212835Min: 32.3 / Avg: 32.57 / Max: 32.8Min: 32.6 / Avg: 32.9 / Max: 33.1

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.030, N = 3SE +/- 0.006, N = 36.0946.1501. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pCPUFreq SchedutilCPUFreq Performance246810Min: 6.04 / Avg: 6.09 / Max: 6.14Min: 6.14 / Avg: 6.15 / Max: 6.161. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 20201218Target: CPU - Model: shufflenet-v2CPUFreq SchedutilCPUFreq Performance0.9991.9982.9973.9964.995SE +/- 0.01, N = 12SE +/- 0.02, N = 34.444.40MIN: 4.35 / MAX: 7.79MIN: 4.33 / MAX: 12.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2CPUFreq SchedutilCPUFreq Performance246810Min: 4.4 / Avg: 4.44 / Max: 4.5Min: 4.38 / Avg: 4.4 / Max: 4.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8CPUFreq SchedutilCPUFreq Performance0.96231.92462.88693.84924.8115SE +/- 0.011, N = 3SE +/- 0.028, N = 34.2774.2391. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8CPUFreq SchedutilCPUFreq Performance246810Min: 4.26 / Avg: 4.28 / Max: 4.3Min: 4.2 / Avg: 4.24 / Max: 4.291. (CXX) g++ options: -O3 -fPIC

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10CPUFreq SchedutilCPUFreq Performance1.14862.29723.44584.59445.743SE +/- 0.029, N = 3SE +/- 0.008, N = 35.0605.105
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10CPUFreq SchedutilCPUFreq Performance246810Min: 5.02 / Avg: 5.06 / Max: 5.12Min: 5.09 / Avg: 5.11 / Max: 5.11

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 AtomsCPUFreq SchedutilCPUFreq Performance0.24470.48940.73410.97881.2235SE +/- 0.00415, N = 3SE +/- 0.00618, N = 31.087451.07820
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsCPUFreq SchedutilCPUFreq Performance246810Min: 1.08 / Avg: 1.09 / Max: 1.1Min: 1.07 / Avg: 1.08 / Max: 1.09

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KSE +/- 8.67, N = 3SE +/- 5.49, N = 312056.3912156.391. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 12041.76 / Avg: 12056.39 / Max: 12071.78Min: 12150.07 / Avg: 12156.39 / Max: 12167.331. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

Timed GDB GNU Debugger Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileCPUFreq SchedutilCPUFreq Performance1428425670SE +/- 0.28, N = 3SE +/- 0.12, N = 362.6262.11
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileCPUFreq SchedutilCPUFreq Performance1224364860Min: 62.3 / Avg: 62.62 / Max: 63.17Min: 61.94 / Avg: 62.11 / Max: 62.35

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 20201218Target: CPU - Model: squeezenet_ssdCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.07, N = 13SE +/- 0.02, N = 314.7014.58MIN: 14.02 / MAX: 23.03MIN: 14.26 / MAX: 15.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdCPUFreq SchedutilCPUFreq Performance48121620Min: 14.22 / Avg: 14.7 / Max: 15.31Min: 14.55 / Avg: 14.58 / Max: 14.611. (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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance306090120150SE +/- 0.88, N = 3SE +/- 0.67, N = 31251261. firefox 84.0.2
OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance20406080100Min: 124 / Avg: 125.33 / Max: 127Min: 125 / Avg: 126.33 / Max: 1271. firefox 84.0.2

FFTE

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

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineCPUFreq SchedutilCPUFreq Performance7K14K21K28K35KSE +/- 60.73, N = 3SE +/- 83.61, N = 334673.8834946.481. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineCPUFreq SchedutilCPUFreq Performance6K12K18K24K30KMin: 34609.06 / Avg: 34673.88 / Max: 34795.24Min: 34799.27 / Avg: 34946.48 / Max: 35088.781. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian DragonCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.11, N = 3SE +/- 0.11, N = 324.8125.00MIN: 24.48 / MAX: 25.28MIN: 24.49 / MAX: 25.5
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian DragonCPUFreq SchedutilCPUFreq Performance612182430Min: 24.6 / Avg: 24.81 / Max: 24.99Min: 24.83 / Avg: 25 / Max: 25.21

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedCPUFreq SchedutilCPUFreq Performance1530456075SE +/- 0.60, N = 3SE +/- 0.07, N = 368.3967.861. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedCPUFreq SchedutilCPUFreq Performance1326395265Min: 67.44 / Avg: 68.39 / Max: 69.5Min: 67.72 / Avg: 67.86 / Max: 67.971. (CC) gcc options: -O3

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelCPUFreq SchedutilCPUFreq Performance306090120150141.30140.21

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsCPUFreq SchedutilCPUFreq Performance918273645SE +/- 0.29, N = 3SE +/- 0.27, N = 338.0337.741. git version 2.27.0
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsCPUFreq SchedutilCPUFreq Performance816243240Min: 37.45 / Avg: 38.03 / Max: 38.35Min: 37.31 / Avg: 37.74 / Max: 38.221. git version 2.27.0

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 4KCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 0.43, N = 3SE +/- 0.61, N = 3238.79236.98MIN: 180.39 / MAX: 246.96MIN: 177.99 / MAX: 245.641. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 4KCPUFreq SchedutilCPUFreq Performance4080120160200Min: 238.02 / Avg: 238.79 / Max: 239.52Min: 235.85 / Avg: 236.98 / Max: 237.931. (CC) gcc options: -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 20201218Target: CPU - Model: efficientnet-b0CPUFreq SchedutilCPUFreq Performance1.2152.433.6454.866.075SE +/- 0.03, N = 14SE +/- 0.01, N = 35.405.36MIN: 5.3 / MAX: 7.34MIN: 5.3 / MAX: 12.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0CPUFreq SchedutilCPUFreq Performance246810Min: 5.36 / Avg: 5.4 / Max: 5.77Min: 5.34 / Avg: 5.36 / Max: 5.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: HighCPUFreq SchedutilCPUFreq Performance120240360480600SE +/- 0.86, N = 3SE +/- 2.00, N = 3540.74544.61MIN: 350 / MAX: 871MIN: 326 / MAX: 876
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: HighCPUFreq SchedutilCPUFreq Performance100200300400500Min: 539.05 / Avg: 540.74 / Max: 541.84Min: 540.76 / Avg: 544.61 / Max: 547.49

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltraCPUFreq SchedutilCPUFreq Performance100200300400500SE +/- 0.46, N = 3SE +/- 0.35, N = 3472.04475.24MIN: 280 / MAX: 740MIN: 258 / MAX: 739
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltraCPUFreq SchedutilCPUFreq Performance80160240320400Min: 471.21 / Avg: 472.04 / Max: 472.79Min: 474.85 / Avg: 475.24 / Max: 475.93

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverCPUFreq SchedutilCPUFreq Performance11002200330044005500SE +/- 80.25, N = 15SE +/- 61.90, N = 155309.465273.761. (CC) gcc options: -O3 -mavx2
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverCPUFreq SchedutilCPUFreq Performance9001800270036004500Min: 4860.05 / Avg: 5309.46 / Max: 5883.06Min: 4879.97 / Avg: 5273.76 / Max: 5660.621. (CC) gcc options: -O3 -mavx2

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 3.43, N = 3SE +/- 5.08, N = 3903.2897.21. firefox 84.0.2
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: FirefoxCPUFreq SchedutilCPUFreq Performance160320480640800Min: 896.3 / Avg: 903.17 / Max: 906.7Min: 888.3 / Avg: 897.23 / Max: 905.91. firefox 84.0.2

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 20201218Target: CPU - Model: mobilenetCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.13, N = 14SE +/- 0.11, N = 312.2012.12MIN: 11.86 / MAX: 24MIN: 11.89 / MAX: 12.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetCPUFreq SchedutilCPUFreq Performance48121620Min: 12 / Avg: 12.2 / Max: 13.71Min: 12.01 / Avg: 12.12 / Max: 12.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

ASKAP

This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - DegriddingCPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 6.34, N = 3SE +/- 1.29, N = 31884.491896.751. (CXX) g++ options: -lpthread
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - DegriddingCPUFreq SchedutilCPUFreq Performance30060090012001500Min: 1872.57 / Avg: 1884.49 / Max: 1894.22Min: 1895.06 / Avg: 1896.75 / Max: 1899.281. (CXX) g++ options: -lpthread

asmFish

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

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthCPUFreq SchedutilCPUFreq Performance13M26M39M52M65MSE +/- 699901.59, N = 4SE +/- 253815.96, N = 35999196260379803
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthCPUFreq SchedutilCPUFreq Performance10M20M30M40M50MMin: 58949879 / Avg: 59991961.75 / Max: 61944225Min: 59873900 / Avg: 60379803.33 / Max: 60669004

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.03, N = 3SE +/- 0.03, N = 316.9917.10MIN: 16.51MIN: 16.561. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance48121620Min: 16.95 / Avg: 16.99 / Max: 17.04Min: 17.07 / Avg: 17.1 / Max: 17.151. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Incompact3D

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 BetterIncompact3D 2020-09-17Input: CylinderCPUFreq SchedutilCPUFreq Performance4080120160200SE +/- 0.06, N = 3SE +/- 0.93, N = 3182.90181.771. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: CylinderCPUFreq SchedutilCPUFreq Performance306090120150Min: 182.79 / Avg: 182.9 / Max: 182.98Min: 180.03 / Avg: 181.77 / Max: 183.221. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Plot3D - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance15K30K45K60K75KSE +/- 58.59, N = 3SE +/- 26.87, N = 36892368498
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Plot3D - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance12K24K36K48K60KMin: 68806 / Avg: 68923 / Max: 68987Min: 68444 / Avg: 68497.67 / Max: 68527

Appleseed

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

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyCPUFreq SchedutilCPUFreq Performance4080120160200190.54189.42

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: LowCPUFreq SchedutilCPUFreq Performance150300450600750SE +/- 8.74, N = 3SE +/- 4.92, N = 3675.27671.34MIN: 432 / MAX: 1414MIN: 428 / MAX: 1388
OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: LowCPUFreq SchedutilCPUFreq Performance120240360480600Min: 661.52 / Avg: 675.27 / Max: 691.5Min: 662.24 / Avg: 671.34 / Max: 679.14

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceCPUFreq SchedutilCPUFreq Performance918273645SE +/- 0.19, N = 3SE +/- 0.14, N = 340.8641.09
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceCPUFreq SchedutilCPUFreq Performance918273645Min: 40.49 / Avg: 40.86 / Max: 41.06Min: 40.9 / Avg: 41.09 / Max: 41.36

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pCPUFreq SchedutilCPUFreq Performance1224364860SE +/- 0.31, N = 3SE +/- 0.29, N = 351.9752.251. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pCPUFreq SchedutilCPUFreq Performance1020304050Min: 51.42 / Avg: 51.97 / Max: 52.51Min: 51.87 / Avg: 52.25 / Max: 52.811. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080CPUFreq SchedutilCPUFreq Performance150300450600750SE +/- 8.64, N = 3SE +/- 6.09, N = 3691.12694.84
OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080CPUFreq SchedutilCPUFreq Performance120240360480600Min: 673.94 / Avg: 691.12 / Max: 701.34Min: 682.94 / Avg: 694.84 / Max: 703.02

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: CrownCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.06, N = 3SE +/- 0.15, N = 324.2924.16MIN: 23.95 / MAX: 24.85MIN: 23.66 / MAX: 24.8
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: CrownCPUFreq SchedutilCPUFreq Performance612182430Min: 24.18 / Avg: 24.29 / Max: 24.36Min: 23.87 / Avg: 24.16 / Max: 24.36

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance90K180K270K360K450KSE +/- 268.53, N = 3SE +/- 46.05, N = 3424552426719
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance70K140K210K280K350KMin: 424052 / Avg: 424551.67 / Max: 424972Min: 426630 / Avg: 426719 / Max: 426784

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance60120180240300SE +/- 3.20, N = 3SE +/- 2.89, N = 3253.02251.731. chrome 88.0.4324.96
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance50100150200250Min: 246.98 / Avg: 253.02 / Max: 257.87Min: 246.29 / Avg: 251.73 / Max: 256.121. chrome 88.0.4324.96

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CCPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 5.60, N = 3SE +/- 9.49, N = 31902.471893.041. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CCPUFreq SchedutilCPUFreq Performance30060090012001500Min: 1893.77 / Avg: 1902.47 / Max: 1912.92Min: 1876.52 / Avg: 1893.04 / Max: 1909.411. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestCPUFreq SchedutilCPUFreq Performance20K40K60K80K100KSE +/- 220.54, N = 3SE +/- 215.71, N = 395640951681. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestCPUFreq SchedutilCPUFreq Performance17K34K51K68K85KMin: 95201 / Avg: 95640.33 / Max: 95894Min: 94739 / Avg: 95168 / Max: 954221. (CXX) g++ options: -pipe -lpthread

Xsbench

XSBench is a mini-app representing a key computational kernel of the Monte Carlo neutronics application OpenMC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06CPUFreq SchedutilCPUFreq Performance700K1400K2100K2800K3500KSE +/- 3010.71, N = 3SE +/- 1024.65, N = 3314166631571431. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm
OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06CPUFreq SchedutilCPUFreq Performance500K1000K1500K2000K2500KMin: 3138015 / Avg: 3141665.67 / Max: 3147638Min: 3155096 / Avg: 3157142.67 / Max: 31582561. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10CPUFreq SchedutilCPUFreq Performance0.92121.84242.76363.68484.606SE +/- 0.024, N = 3SE +/- 0.025, N = 34.0944.0741. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10CPUFreq SchedutilCPUFreq Performance246810Min: 4.06 / Avg: 4.09 / Max: 4.14Min: 4.03 / Avg: 4.07 / Max: 4.111. (CXX) g++ options: -O3 -fPIC

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity 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.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.00, N = 3SE +/- 0.02, N = 38.268.22MIN: 8.13 / MAX: 8.4MIN: 8.13 / MAX: 8.4
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance3691215Min: 8.26 / Avg: 8.26 / Max: 8.26Min: 8.2 / Avg: 8.22 / Max: 8.26

Algebraic Multi-Grid Benchmark

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

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2CPUFreq SchedutilCPUFreq Performance50M100M150M200M250MSE +/- 1232320.79, N = 3SE +/- 399530.94, N = 32092375332102542671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2CPUFreq SchedutilCPUFreq Performance40M80M120M160M200MMin: 206778700 / Avg: 209237533.33 / Max: 210613400Min: 209472100 / Avg: 210254266.67 / Max: 2107869001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.02, N = 3SE +/- 0.13, N = 313.0512.99
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsCPUFreq SchedutilCPUFreq Performance48121620Min: 13.02 / Avg: 13.05 / Max: 13.1Min: 12.76 / Avg: 12.99 / Max: 13.21

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 1080pCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 4.51, N = 3SE +/- 6.19, N = 3924.64929.05MIN: 670.54 / MAX: 1012.49MIN: 618.04 / MAX: 1013.651. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 1080pCPUFreq SchedutilCPUFreq Performance160320480640800Min: 917.34 / Avg: 924.64 / Max: 932.87Min: 916.74 / Avg: 929.05 / Max: 936.341. (CC) gcc options: -pthread

XZ Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9CPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.13, N = 3SE +/- 0.23, N = 322.9923.101. (CC) gcc options: -pthread -fvisibility=hidden -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9CPUFreq SchedutilCPUFreq Performance510152025Min: 22.86 / Avg: 22.99 / Max: 23.25Min: 22.71 / Avg: 23.1 / Max: 23.521. (CC) gcc options: -pthread -fvisibility=hidden -O2

BLAKE2

This is a benchmark of BLAKE2 using the blake2s binary. BLAKE2 is a high-performance crypto alternative to MD5 and SHA-2/3. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 20170307CPUFreq SchedutilCPUFreq Performance0.99681.99362.99043.98724.984SE +/- 0.02, N = 3SE +/- 0.02, N = 34.414.431. (CC) gcc options: -O3 -march=native -lcrypto -lz
OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 20170307CPUFreq SchedutilCPUFreq Performance246810Min: 4.38 / Avg: 4.41 / Max: 4.45Min: 4.38 / Avg: 4.43 / Max: 4.451. (CC) gcc options: -O3 -march=native -lcrypto -lz

TTSIOD 3D Renderer

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

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 3.49, N = 3SE +/- 4.16, N = 31037.511042.101. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingCPUFreq SchedutilCPUFreq Performance2004006008001000Min: 1032.63 / Avg: 1037.51 / Max: 1044.28Min: 1034.02 / Avg: 1042.1 / Max: 1047.891. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

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 20.1Input: Carbon NanotubeCPUFreq SchedutilCPUFreq Performance70140210280350SE +/- 0.52, N = 3SE +/- 0.20, N = 3326.38325.011. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 20.1Input: Carbon NanotubeCPUFreq SchedutilCPUFreq Performance60120180240300Min: 325.43 / Avg: 326.38 / Max: 327.24Min: 324.63 / Avg: 325.01 / Max: 325.321. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: x25xCPUFreq SchedutilCPUFreq Performance130260390520650SE +/- 3.36, N = 3SE +/- 4.18, N = 3623.19620.601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: x25xCPUFreq SchedutilCPUFreq Performance110220330440550Min: 617.56 / Avg: 623.19 / Max: 629.19Min: 612.44 / Avg: 620.6 / Max: 626.241. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.21, N = 3SE +/- 0.21, N = 327.3727.251. (CC) gcc options: -lm -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeCPUFreq SchedutilCPUFreq Performance612182430Min: 26.98 / Avg: 27.37 / Max: 27.69Min: 26.84 / Avg: 27.25 / Max: 27.51. (CC) gcc options: -lm -O3

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.06, N = 3SE +/- 0.04, N = 329.5129.63
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesCPUFreq SchedutilCPUFreq Performance714212835Min: 29.45 / Avg: 29.51 / Max: 29.63Min: 29.58 / Avg: 29.63 / Max: 29.7

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPCPUFreq SchedutilCPUFreq Performance6K12K18K24K30KSE +/- 377.86, N = 3SE +/- 308.13, N = 527738.2927852.001. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPCPUFreq SchedutilCPUFreq Performance5K10K15K20K25KMin: 27276.91 / Avg: 27738.29 / Max: 28487.32Min: 27160.4 / Avg: 27852 / Max: 28609.011. (CXX) g++ options: -O3 -march=native -fopenmp

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity 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.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance0.55581.11161.66742.22322.779SE +/- 0.01, N = 3SE +/- 0.00, N = 32.472.46MIN: 2.44 / MAX: 2.51MIN: 2.44 / MAX: 2.5
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance246810Min: 2.45 / Avg: 2.47 / Max: 2.48Min: 2.46 / Avg: 2.46 / Max: 2.46

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2CPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 1.57, N = 3SE +/- 0.98, N = 3214.93215.80MIN: 209.92 / MAX: 253.5MIN: 213.88 / MAX: 220.61. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2CPUFreq SchedutilCPUFreq Performance4080120160200Min: 212.07 / Avg: 214.92 / Max: 217.49Min: 214.21 / Avg: 215.8 / Max: 217.581. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: MagiCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 1.73, N = 3SE +/- 0.57, N = 3867.39863.901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: MagiCPUFreq SchedutilCPUFreq Performance150300450600750Min: 864.19 / Avg: 867.39 / Max: 870.15Min: 863.04 / Avg: 863.9 / Max: 864.991. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.08, N = 3SE +/- 0.15, N = 312.4712.42
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentCPUFreq SchedutilCPUFreq Performance48121620Min: 12.33 / Avg: 12.47 / Max: 12.59Min: 12.25 / Avg: 12.42 / Max: 12.73

Aircrack-ng

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

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.2CPUFreq SchedutilCPUFreq Performance16K32K48K64K80KSE +/- 93.65, N = 3SE +/- 56.42, N = 374981.0275278.801. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.2CPUFreq SchedutilCPUFreq Performance13K26K39K52K65KMin: 74794.27 / Avg: 74981.02 / Max: 75086.86Min: 75178.83 / Avg: 75278.8 / Max: 75374.111. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkCPUFreq SchedutilCPUFreq Performance0.28460.56920.85381.13841.423SE +/- 0.004, N = 3SE +/- 0.002, N = 31.2601.2651. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkCPUFreq SchedutilCPUFreq Performance246810Min: 1.25 / Avg: 1.26 / Max: 1.27Min: 1.26 / Avg: 1.27 / Max: 1.271. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Primesieve

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

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number GenerationCPUFreq SchedutilCPUFreq Performance3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 311.1511.111. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number GenerationCPUFreq SchedutilCPUFreq Performance3691215Min: 11.1 / Avg: 11.15 / Max: 11.19Min: 11.07 / Avg: 11.11 / Max: 11.141. (CXX) g++ options: -O3 -lpthread

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 2.24, N = 3SE +/- 0.00, N = 3987.0990.61. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance2004006008001000Min: 982.9 / Avg: 987 / Max: 990.6Min: 990.6 / Avg: 990.6 / Max: 990.61. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 1CPUFreq SchedutilCPUFreq Performance0.12530.25060.37590.50120.6265SE +/- 0.002, N = 3SE +/- 0.001, N = 30.5550.557
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 1CPUFreq SchedutilCPUFreq Performance246810Min: 0.55 / Avg: 0.56 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.56

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileCPUFreq SchedutilCPUFreq Performance20406080100SE +/- 0.07, N = 3SE +/- 0.22, N = 379.5779.29
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileCPUFreq SchedutilCPUFreq Performance1530456075Min: 79.44 / Avg: 79.57 / Max: 79.69Min: 79.04 / Avg: 79.29 / Max: 79.73

Warsow

This is a benchmark of Warsow, a popular open-source first-person shooter. This game uses the QFusion engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 1920 x 1080CPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 1.03, N = 3SE +/- 1.06, N = 3957.9961.1
OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 1920 x 1080CPUFreq SchedutilCPUFreq Performance2004006008001000Min: 955.9 / Avg: 957.9 / Max: 959.3Min: 959 / Avg: 961.1 / Max: 962.4

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance90180270360450SE +/- 0.30, N = 3SE +/- 1.23, N = 3432.7431.3
OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance80160240320400Min: 432.3 / Avg: 432.73 / Max: 433.3Min: 428.9 / Avg: 431.33 / Max: 432.8

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance0.54691.09381.64072.18762.7345SE +/- 0.00633, N = 3SE +/- 0.00800, N = 32.430832.42349MIN: 2.31MIN: 2.31. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance246810Min: 2.42 / Avg: 2.43 / Max: 2.44Min: 2.41 / Avg: 2.42 / Max: 2.441. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

ASKAP

This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - GriddingCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 1.35, N = 3SE +/- 0.30, N = 3915.04917.731. (CXX) g++ options: -lpthread
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - GriddingCPUFreq SchedutilCPUFreq Performance160320480640800Min: 913.6 / Avg: 915.04 / Max: 917.73Min: 917.14 / Avg: 917.73 / Max: 918.121. (CXX) g++ options: -lpthread

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLCPUFreq SchedutilCPUFreq Performance50100150200250SE +/- 1.43, N = 3SE +/- 0.48, N = 3241.4242.1MAX: 356.9MAX: 355.7
OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLCPUFreq SchedutilCPUFreq Performance4080120160200Min: 239.9 / Avg: 241.43 / Max: 244.3Min: 241.1 / Avg: 242.07 / Max: 242.6

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28CPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.02, N = 3SE +/- 0.08, N = 315.3415.381. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28CPUFreq SchedutilCPUFreq Performance48121620Min: 15.31 / Avg: 15.34 / Max: 15.37Min: 15.26 / Avg: 15.38 / Max: 15.541. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

Tachyon

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeCPUFreq SchedutilCPUFreq Performance1020304050SE +/- 0.09, N = 3SE +/- 0.05, N = 344.4444.321. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeCPUFreq SchedutilCPUFreq Performance918273645Min: 44.28 / Avg: 44.44 / Max: 44.58Min: 44.23 / Avg: 44.32 / Max: 44.41. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondCPUFreq SchedutilCPUFreq Performance200K400K600K800K1000KSE +/- 1206.35, N = 3SE +/- 140.65, N = 3813873.28816060.571. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondCPUFreq SchedutilCPUFreq Performance140K280K420K560K700KMin: 811461.9 / Avg: 813873.28 / Max: 815148.17Min: 815806.25 / Avg: 816060.57 / Max: 816291.821. (CC) gcc options: -O2 -lrt" -lrt

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.020, N = 5SE +/- 0.032, N = 56.3326.3491. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACCPUFreq SchedutilCPUFreq Performance3691215Min: 6.29 / Avg: 6.33 / Max: 6.39Min: 6.3 / Avg: 6.35 / Max: 6.471. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileCPUFreq SchedutilCPUFreq Performance20406080100SE +/- 0.05, N = 3SE +/- 0.11, N = 381.5781.37
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileCPUFreq SchedutilCPUFreq Performance1632486480Min: 81.48 / Avg: 81.57 / Max: 81.62Min: 81.25 / Avg: 81.37 / Max: 81.59

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomCPUFreq SchedutilCPUFreq Performance0.9321.8642.7963.7284.66SE +/- 0.005, N = 3SE +/- 0.017, N = 34.1424.132
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomCPUFreq SchedutilCPUFreq Performance246810Min: 4.13 / Avg: 4.14 / Max: 4.15Min: 4.1 / Avg: 4.13 / Max: 4.16

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPCPUFreq SchedutilCPUFreq Performance9K18K27K36K45KSE +/- 144.00, N = 3SE +/- 199.58, N = 339803.7839899.161. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPCPUFreq SchedutilCPUFreq Performance7K14K21K28K35KMin: 39627.9 / Avg: 39803.78 / Max: 40089.23Min: 39682.16 / Avg: 39899.16 / Max: 40297.791. (CXX) g++ options: -O3 -march=native -fopenmp

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileCPUFreq SchedutilCPUFreq Performance20K40K60K80K100KSE +/- 290.71, N = 3SE +/- 261.83, N = 3103996104235
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileCPUFreq SchedutilCPUFreq Performance20K40K60K80K100KMin: 103512 / Avg: 103996 / Max: 104517Min: 103935 / Avg: 104235.33 / Max: 104757

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 20201218Target: CPU-v2-v2 - Model: mobilenet-v2CPUFreq SchedutilCPUFreq Performance1.00582.01163.01744.02325.029SE +/- 0.00, N = 14SE +/- 0.01, N = 34.464.47MIN: 4.29 / MAX: 5.81MIN: 4.29 / MAX: 11.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2CPUFreq SchedutilCPUFreq Performance246810Min: 4.44 / Avg: 4.46 / Max: 4.48Min: 4.45 / Avg: 4.47 / Max: 4.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1CPUFreq SchedutilCPUFreq Performance0.95791.91582.87373.83164.7895SE +/- 0.00430, N = 3SE +/- 0.00194, N = 34.248244.257551. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1CPUFreq SchedutilCPUFreq Performance246810Min: 4.24 / Avg: 4.25 / Max: 4.25Min: 4.25 / Avg: 4.26 / Max: 4.261. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Appleseed

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

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterCPUFreq SchedutilCPUFreq Performance306090120150112.25112.49

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 4KCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.06, N = 3SE +/- 0.11, N = 328.0728.011. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KCPUFreq SchedutilCPUFreq Performance612182430Min: 27.96 / Avg: 28.07 / Max: 28.13Min: 27.79 / Avg: 28.01 / Max: 28.171. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: CrownCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.06, N = 3SE +/- 0.15, N = 323.8523.80MIN: 23.52 / MAX: 24.46MIN: 23.36 / MAX: 24.63
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: CrownCPUFreq SchedutilCPUFreq Performance612182430Min: 23.73 / Avg: 23.85 / Max: 23.92Min: 23.57 / Avg: 23.8 / Max: 24.07

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance0.79671.59342.39013.18683.9835SE +/- 0.00511, N = 3SE +/- 0.00567, N = 33.540693.53364MIN: 3.42MIN: 3.41. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUCPUFreq SchedutilCPUFreq Performance246810Min: 3.53 / Avg: 3.54 / Max: 3.55Min: 3.53 / Avg: 3.53 / Max: 3.541. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance10002000300040005000SE +/- 2.85, N = 3SE +/- 4.06, N = 346204611
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance8001600240032004000Min: 4614 / Avg: 4619.67 / Max: 4623Min: 4604 / Avg: 4611.33 / Max: 4618

Rust Prime Benchmark

Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000CPUFreq SchedutilCPUFreq Performance1.1662.3323.4984.6645.83SE +/- 0.001, N = 3SE +/- 0.001, N = 35.1825.1721. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000CPUFreq SchedutilCPUFreq Performance246810Min: 5.18 / Avg: 5.18 / Max: 5.18Min: 5.17 / Avg: 5.17 / Max: 5.171. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity 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.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance1.23752.4753.71254.956.1875SE +/- 0.00, N = 3SE +/- 0.01, N = 35.495.50MIN: 5.43 / MAX: 5.59MIN: 5.43 / MAX: 5.59
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance246810Min: 5.49 / Avg: 5.49 / Max: 5.49Min: 5.49 / Avg: 5.5 / Max: 5.52

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPUCPUFreq SchedutilCPUFreq Performance7K14K21K28K35KSE +/- 130.41, N = 3SE +/- 29.42, N = 33250832451
OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPUCPUFreq SchedutilCPUFreq Performance6K12K18K24K30KMin: 32360 / Avg: 32508 / Max: 32768Min: 32395 / Avg: 32450.67 / Max: 32495

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisCPUFreq SchedutilCPUFreq Performance1428425670SE +/- 0.14, N = 3SE +/- 0.10, N = 362.9962.881. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisCPUFreq SchedutilCPUFreq Performance1224364860Min: 62.71 / Avg: 62.99 / Max: 63.14Min: 62.7 / Avg: 62.88 / Max: 63.031. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarCPUFreq SchedutilCPUFreq Performance246810SE +/- 0.013, N = 3SE +/- 0.016, N = 38.6748.659
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarCPUFreq SchedutilCPUFreq Performance3691215Min: 8.65 / Avg: 8.67 / Max: 8.7Min: 8.63 / Avg: 8.66 / Max: 8.68

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastCPUFreq SchedutilCPUFreq Performance1224364860SE +/- 0.11, N = 3SE +/- 0.04, N = 353.4053.311. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastCPUFreq SchedutilCPUFreq Performance1122334455Min: 53.21 / Avg: 53.4 / Max: 53.58Min: 53.23 / Avg: 53.31 / Max: 53.381. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Hugin

Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeCPUFreq SchedutilCPUFreq Performance816243240SE +/- 0.34, N = 3SE +/- 0.21, N = 334.0834.02
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeCPUFreq SchedutilCPUFreq Performance714212835Min: 33.44 / Avg: 34.08 / Max: 34.61Min: 33.6 / Avg: 34.02 / Max: 34.26

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CPUFreq SchedutilCPUFreq Performance300K600K900K1200K1500KSE +/- 786.91, N = 3SE +/- 628.82, N = 312172001215293
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CPUFreq SchedutilCPUFreq Performance200K400K600K800K1000KMin: 1215760 / Avg: 1217200 / Max: 1218470Min: 1214040 / Avg: 1215293.33 / Max: 1216010

VKMark

VKMark is a collection of Vulkan tests/benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance140280420560700SE +/- 0.33, N = 36406411. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance110220330440550Min: 641 / Avg: 641.33 / Max: 6421. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5CPUFreq SchedutilCPUFreq Performance500K1000K1500K2000K2500KSE +/- 4041.45, N = 3SE +/- 2403.70, N = 3221700022203331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5CPUFreq SchedutilCPUFreq Performance400K800K1200K1600K2000KMin: 2210000 / Avg: 2217000 / Max: 2224000Min: 2217000 / Avg: 2220333.33 / Max: 22250001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishCPUFreq SchedutilCPUFreq Performance8K16K24K32K40KSE +/- 108.56, N = 3SE +/- 92.81, N = 338256383111. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishCPUFreq SchedutilCPUFreq Performance7K14K21K28K35KMin: 38080 / Avg: 38255.67 / Max: 38454Min: 38137 / Avg: 38311 / Max: 384541. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 1.20, N = 3SE +/- 1.15, N = 320912094
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance400800120016002000Min: 2089 / Avg: 2090.67 / Max: 2093Min: 2092 / Avg: 2094 / Max: 2096

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 TimeCPUFreq SchedutilCPUFreq Performance2M4M6M8M10MSE +/- 63865.50, N = 3SE +/- 7590.56, N = 311356738113726471. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeCPUFreq SchedutilCPUFreq Performance2M4M6M8M10MMin: 11232684 / Avg: 11356738.33 / Max: 11445115Min: 11357932 / Avg: 11372646.67 / Max: 113832381. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

YafaRay

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

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneCPUFreq SchedutilCPUFreq Performance1530456075SE +/- 0.20, N = 3SE +/- 0.37, N = 366.5866.671. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneCPUFreq SchedutilCPUFreq Performance1326395265Min: 66.21 / Avg: 66.58 / Max: 66.91Min: 66.05 / Avg: 66.67 / Max: 67.331. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCPUFreq SchedutilCPUFreq Performance15K30K45K60K75KSE +/- 67.19, N = 3SE +/- 59.47, N = 368077.267985.1
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCPUFreq SchedutilCPUFreq Performance12K24K36K48K60KMin: 67956.9 / Avg: 68077.2 / Max: 68189.2Min: 67886.5 / Avg: 67985.13 / Max: 68092

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathCPUFreq SchedutilCPUFreq Performance40K80K120K160K200KSE +/- 139.54, N = 3SE +/- 124.62, N = 3172877.32173101.001. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathCPUFreq SchedutilCPUFreq Performance30K60K90K120K150KMin: 172681.42 / Avg: 172877.32 / Max: 173147.4Min: 172939.24 / Avg: 173101 / Max: 173346.11. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPUCPUFreq SchedutilCPUFreq Performance20K40K60K80K100KSE +/- 118.62, N = 3SE +/- 97.17, N = 390585.2290701.131. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPUCPUFreq SchedutilCPUFreq Performance16K32K48K64K80KMin: 90431.96 / Avg: 90585.22 / Max: 90818.69Min: 90523.29 / Avg: 90701.13 / Max: 90857.91. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

C-Ray

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

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.04, N = 3SE +/- 0.04, N = 330.8730.901. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelCPUFreq SchedutilCPUFreq Performance714212835Min: 30.8 / Avg: 30.87 / Max: 30.93Min: 30.85 / Avg: 30.9 / Max: 30.981. (CC) gcc options: -lm -lpthread -O3

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CPUFreq SchedutilCPUFreq Performance300K600K900K1200K1500KSE +/- 501.54, N = 3SE +/- 583.87, N = 313528331351330
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CPUFreq SchedutilCPUFreq Performance200K400K600K800K1000KMin: 1351860 / Avg: 1352833.33 / Max: 1353530Min: 1350200 / Avg: 1351330 / Max: 1352150

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.17, N = 15SE +/- 0.31, N = 324.6724.651. chrome 88.0.4324.96
OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google ChromeCPUFreq SchedutilCPUFreq Performance612182430Min: 23.55 / Avg: 24.67 / Max: 26.05Min: 24.09 / Avg: 24.65 / Max: 25.151. chrome 88.0.4324.96

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedCPUFreq SchedutilCPUFreq Performance1632486480SE +/- 0.78, N = 5SE +/- 0.86, N = 470.1370.201. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedCPUFreq SchedutilCPUFreq Performance1428425670Min: 69.04 / Avg: 70.13 / Max: 73.23Min: 69.08 / Avg: 70.2 / Max: 72.771. (CC) gcc options: -O3

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionCPUFreq SchedutilCPUFreq Performance612182430SE +/- 0.04, N = 3SE +/- 0.03, N = 327.1727.151. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionCPUFreq SchedutilCPUFreq Performance612182430Min: 27.13 / Avg: 27.17 / Max: 27.24Min: 27.11 / Avg: 27.15 / Max: 27.211. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KSE +/- 7.17, N = 3SE +/- 4.48, N = 31087010861
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance2K4K6K8K10KMin: 10856 / Avg: 10870.33 / Max: 10878Min: 10855 / Avg: 10861.33 / Max: 10870

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesCPUFreq SchedutilCPUFreq Performance1.10882.21763.32644.43525.544SE +/- 0.011, N = 3SE +/- 0.023, N = 34.9244.9281. (CXX) g++ options: -fopenmp -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesCPUFreq SchedutilCPUFreq Performance246810Min: 4.91 / Avg: 4.92 / Max: 4.95Min: 4.9 / Avg: 4.93 / Max: 4.971. (CXX) g++ options: -fopenmp -O3

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance4080120160200SE +/- 0.56, N = 3SE +/- 0.13, N = 3197.32197.16
OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance4080120160200Min: 196.43 / Avg: 197.32 / Max: 198.35Min: 196.91 / Avg: 197.16 / Max: 197.34

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance400800120016002000SE +/- 5.80, N = 3SE +/- 1.35, N = 32056.322054.67
OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance400800120016002000Min: 2047.08 / Avg: 2056.32 / Max: 2067.02Min: 2052.03 / Avg: 2054.66 / Max: 2056.47

GLmark2

This is a test of Linaro's glmark2 port, currently using the X11 OpenGL 2.0 target. GLmark2 is a basic OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance600120018002400300028732875

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance90180270360450SE +/- 2.11, N = 3SE +/- 4.45, N = 3426.41426.69
OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160CPUFreq SchedutilCPUFreq Performance80160240320400Min: 422.58 / Avg: 426.41 / Max: 429.85Min: 417.79 / Avg: 426.69 / Max: 431.26

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 20201218Target: CPU - Model: regnety_400mCPUFreq SchedutilCPUFreq Performance48121620SE +/- 0.02, N = 14SE +/- 0.06, N = 317.7417.75MIN: 17.48 / MAX: 21.04MIN: 17.47 / MAX: 21.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mCPUFreq SchedutilCPUFreq Performance48121620Min: 17.63 / Avg: 17.74 / Max: 17.98Min: 17.63 / Avg: 17.75 / Max: 17.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance4K8K12K16K20KSE +/- 5.86, N = 3SE +/- 4.67, N = 31959719608
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance3K6K9K12K15KMin: 19588 / Avg: 19597 / Max: 19608Min: 19603 / Avg: 19607.67 / Max: 19617

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: MemoryCPUFreq SchedutilCPUFreq Performance3M6M9M12M15MSE +/- 5094.96, N = 3SE +/- 25904.74, N = 315419966.3615428518.921. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: MemoryCPUFreq SchedutilCPUFreq Performance3M6M9M12M15MMin: 15411873.14 / Avg: 15419966.36 / Max: 15429374.95Min: 15376825.38 / Avg: 15428518.92 / Max: 15457365.71. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCPUFreq SchedutilCPUFreq Performance20K40K60K80K100KSE +/- 109.89, N = 3SE +/- 71.83, N = 395054.495103.9
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCPUFreq SchedutilCPUFreq Performance16K32K48K64K80KMin: 94851.7 / Avg: 95054.43 / Max: 95229.3Min: 94961.9 / Avg: 95103.93 / Max: 95193.6

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoCPUFreq SchedutilCPUFreq Performance10002000300040005000SE +/- 11.74, N = 3SE +/- 13.34, N = 34838.184840.501. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoCPUFreq SchedutilCPUFreq Performance8001600240032004000Min: 4823.82 / Avg: 4838.18 / Max: 4861.45Min: 4823.04 / Avg: 4840.5 / Max: 4866.711. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkCPUFreq SchedutilCPUFreq Performance1224364860SE +/- 0.08, N = 3SE +/- 0.07, N = 354.1154.091. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkCPUFreq SchedutilCPUFreq Performance1122334455Min: 53.96 / Avg: 54.11 / Max: 54.23Min: 53.99 / Avg: 54.09 / Max: 54.221. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCPUFreq SchedutilCPUFreq Performance13K26K39K52K65KSE +/- 36.69, N = 3SE +/- 31.91, N = 362792.562771.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCPUFreq SchedutilCPUFreq Performance11K22K33K44K55KMin: 62750.1 / Avg: 62792.53 / Max: 62865.6Min: 62727.6 / Avg: 62771.57 / Max: 62833.6

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveCPUFreq SchedutilCPUFreq Performance20406080100SE +/- 0.11, N = 3SE +/- 0.05, N = 3100.62100.591. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveCPUFreq SchedutilCPUFreq Performance20406080100Min: 100.4 / Avg: 100.62 / Max: 100.77Min: 100.49 / Avg: 100.59 / Max: 100.661. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance2004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 3846846
OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 3840 x 2160 - Mode: FullscreenCPUFreq SchedutilCPUFreq Performance150300450600750Min: 846 / Avg: 846.33 / Max: 847Min: 846 / Avg: 846.33 / Max: 847

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLCPUFreq SchedutilCPUFreq Performance20406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 396.496.4MAX: 119.3MAX: 119.9
OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 3840 x 2160 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLCPUFreq SchedutilCPUFreq Performance20406080100Min: 96.4 / Avg: 96.43 / Max: 96.5Min: 96.4 / Avg: 96.43 / Max: 96.5

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 20201218Target: CPU-v3-v3 - Model: mobilenet-v3CPUFreq SchedutilCPUFreq Performance0.9361.8722.8083.7444.68SE +/- 0.00, N = 14SE +/- 0.00, N = 34.164.16MIN: 4.1 / MAX: 5.46MIN: 4.11 / MAX: 5.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3CPUFreq SchedutilCPUFreq Performance246810Min: 4.14 / Avg: 4.16 / Max: 4.21Min: 4.15 / Avg: 4.16 / Max: 4.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.05, N = 3SE +/- 0.09, N = 329.3529.351. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastCPUFreq SchedutilCPUFreq Performance714212835Min: 29.25 / Avg: 29.35 / Max: 29.43Min: 29.17 / Avg: 29.35 / Max: 29.481. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity 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.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance0.66151.3231.98452.6463.3075SE +/- 0.00, N = 3SE +/- 0.00, N = 32.942.94MIN: 2.92 / MAX: 2.98MIN: 2.92 / MAX: 2.99
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerCPUFreq SchedutilCPUFreq Performance246810Min: 2.93 / Avg: 2.94 / Max: 2.94Min: 2.94 / Avg: 2.94 / Max: 2.95

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance9182736454040MAX: 41.67MIN: 38.46 / MAX: 41.67

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance714212835SE +/- 0.30, N = 3SE +/- 0.30, N = 330.0130.01MIN: 28.57 / MAX: 32.26MIN: 29.41 / MAX: 32.26
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisCPUFreq SchedutilCPUFreq Performance714212835Min: 29.41 / Avg: 30.01 / Max: 30.3Min: 29.41 / Avg: 30.01 / Max: 30.3

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19CPUFreq SchedutilCPUFreq Performance1020304050SE +/- 0.06, N = 3SE +/- 0.06, N = 343.443.41. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19CPUFreq SchedutilCPUFreq Performance918273645Min: 43.3 / Avg: 43.4 / Max: 43.5Min: 43.3 / Avg: 43.4 / Max: 43.51. (CC) gcc options: -O3 -pthread -lz -llzma

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database ShootoutCPUFreq SchedutilCPUFreq Performance6001200180024003000SE +/- 49.45, N = 25SE +/- 25.42, N = 62850.402597.43
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database ShootoutCPUFreq SchedutilCPUFreq Performance5001000150020002500Min: 2589.17 / Avg: 2850.4 / Max: 3410.37Min: 2497.31 / Avg: 2597.43 / Max: 2665.77

220 Results Shown

DDraceNetwork:
  3840 x 2160 - Fullscreen - OpenGL 3.3 - Default - Multeasymap - Total Frame Time
  3840 x 2160 - Fullscreen - OpenGL 2.0 - Default - Multeasymap - Total Frame Time
DaCapo Benchmark
FFmpeg
dav1d
AOM AV1
Selenium
DeepSpeech
Selenium
CP2K Molecular Dynamics
Selenium
AOM AV1
Selenium
C-Blosc
Selenium:
  ARES-6 - Google Chrome
  Speedometer - Google Chrome
  ARES-6 - Firefox
DDraceNetwork
LeelaChessZero
oneDNN
Mobile Neural Network
LeelaChessZero
Stress-NG
GIMP
CLOMP
ParaView:
  Wavelet Volume - 3840 x 2160:
    MiVoxels / Sec
    Frames / Sec
NAS Parallel Benchmarks
GIMP:
  resize
  auto-levels
NCNN
oneDNN
Selenium
Node.js V8 Web Tooling Benchmark
Mobile Neural Network
oneDNN
GIMP
ACES DGEMM
NAS Parallel Benchmarks
PlaidML
oneDNN
NCNN
Stockfish
NAS Parallel Benchmarks
PlaidML
NCNN
AI Benchmark Alpha
DaCapo Benchmark
Kripke
NAS Parallel Benchmarks
yquake2
TNN
SVT-VP9
NCNN
rav1e
ASKAP
Timed Linux Kernel Compilation
AI Benchmark Alpha
Swet
NCNN
Timed MAFFT Alignment
Rust Mandelbrot
Renaissance
ASKAP
SVT-VP9
rav1e
Selenium
Tesseract OCR
NCNN
Stress-NG
Renaissance
Cpuminer-Opt
OSPray
Selenium
WebP Image Encode
GEGL
Renaissance
AI Benchmark Alpha
NAS Parallel Benchmarks
Selenium
LZ4 Compression
dav1d
Embree
NAS Parallel Benchmarks
PlaidML
Xonotic
DDraceNetwork
NCNN
Zstd Compression
NCNN
CloverLeaf
LZ4 Compression
x264
Selenium
NeatBench
SVT-AV1
NCNN
libavif avifenc
rav1e
NAMD
NAS Parallel Benchmarks
Timed GDB GNU Debugger Compilation
NCNN
Selenium
FFTE
Embree
LZ4 Compression
Radiance Benchmark
Git
dav1d
NCNN
Xonotic:
  3840 x 2160 - High
  3840 x 2160 - Ultra
Himeno Benchmark
Selenium
NCNN
ASKAP
asmFish
oneDNN
Incompact3D
GpuTest
Appleseed
Xonotic
GEGL
SVT-AV1
Tesseract
Embree
GpuTest
Selenium
NAS Parallel Benchmarks
7-Zip Compression
Xsbench
libavif avifenc
OSPray
Algebraic Multi-Grid Benchmark
Dolfyn
dav1d
XZ Compression
BLAKE2
TTSIOD 3D Renderer
GPAW
Cpuminer-Opt
AOBench
GEGL
FinanceBench
OSPray
TNN
Cpuminer-Opt
OCRMyPDF
Aircrack-ng
GROMACS
Primesieve
yquake2
rav1e
Timed Godot Game Engine Compilation
Warsow:
  1920 x 1080
  3840 x 2160
oneDNN
ASKAP
Unigine Superposition
RNNoise
Tachyon
Coremark
FLAC Audio Encoding
Build2
IndigoBench
FinanceBench
TensorFlow Lite
NCNN
High Performance Conjugate Gradient
Appleseed
x265
Embree
oneDNN
GpuTest
Rust Prime Benchmark
OSPray
Chaos Group V-RAY
Timed MrBayes Analysis
IndigoBench
Kvazaar
Hugin
TensorFlow Lite
VKMark
John The Ripper:
  MD5
  Blowfish
GpuTest
Crafty
YafaRay
TensorFlow Lite
Stress-NG
Sysbench
C-Ray
TensorFlow Lite
Selenium
LZ4 Compression
WebP Image Encode
GpuTest
Smallpt
ParaView:
  Wavelet Contour - 3840 x 2160:
    Frames / Sec
    MiPolys / Sec
GLmark2
Tesseract
NCNN
GpuTest
Sysbench
TensorFlow Lite
Stress-NG
LibRaw
TensorFlow Lite
ASTC Encoder
GpuTest
Unigine Superposition
NCNN
Kvazaar
OSPray:
  XFrog Forest - Path Tracer
  NASA Streamlines - SciVis
  San Miguel - SciVis
Zstd Compression
Renaissance

CPUFreq Schedutil

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 January 2021 18:09 by user phoronix.

CPUFreq Performance

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3202 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.10, Kernel: 5.11.0-rc4-max-boost-inv-patch (x86_64) 20210121, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 21.0.0-devel (git-f01bca8 2021-01-08 groovy-oibaf-ppa) (LLVM 11.0.1), Vulkan: 1.2.164, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 January 2021 18:37 by user pts.