Ryzen 3 1300X

AMD Ryzen 3 1300X testing with a ASRock AB350 Pro4 (P3.20 BIOS) and Sapphire AMD Radeon R7 260X/360 2GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010223-FI-RYZEN313077
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 4 Tests
Bioinformatics 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 17 Tests
Compression Tests 3 Tests
CPU Massive 23 Tests
Creator Workloads 27 Tests
Database Test Suite 4 Tests
Encoding 7 Tests
Fortran Tests 5 Tests
Game Development 2 Tests
HPC - High Performance Computing 21 Tests
Imaging 8 Tests
Java 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 10 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 4 Tests
Multi-Core 23 Tests
NVIDIA GPU Compute 8 Tests
OCR 2 Tests
Intel oneAPI 2 Tests
OpenCV Tests 2 Tests
OpenMPI Tests 5 Tests
Productivity 3 Tests
Programmer / Developer System Benchmarks 7 Tests
Python 2 Tests
Renderers 3 Tests
Scientific Computing 10 Tests
Server 4 Tests
Server CPU Tests 13 Tests
Single-Threaded 4 Tests
Speech 2 Tests
Telephony 2 Tests
Texture Compression 2 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 5.4
October 19 2020
  17 Hours, 35 Minutes
Linux 5.9.1
October 20 2020
  17 Hours, 40 Minutes
Linux 5.10 Git
October 21 2020
  18 Hours, 30 Minutes
Invert Hiding All Results Option
  17 Hours, 55 Minutes

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

Linux 5.4

Processor: AMD Ryzen 3 1300X @ 3.50GHz (4 Cores), Motherboard: ASRock AB350 Pro4 (P3.20 BIOS), Chipset: AMD 17h, Memory: 8GB, Disk: 128GB ADATA SU800, Graphics: Sapphire AMD Radeon R7 260X/360 2GB, Audio: AMD Tobago HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.4.0-51-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 ondemand - CPU Microcode: 0x8001129
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.9.1

OS: Ubuntu 20.04, Kernel: 5.9.1-050901-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.5 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Linux 5.10 Git

OS: Ubuntu 20.04, Kernel: 5.9.0-050900daily20201021-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.5 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Ryzen 3 1300XProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionOpenGLLinux 5.4Linux 5.9.1Linux 5.10 GitAMD Ryzen 3 1300X @ 3.50GHz (4 Cores)ASRock AB350 Pro4 (P3.20 BIOS)AMD 17h8GB128GB ADATA SU800Sapphire AMD Radeon R7 260X/360 2GBAMD Tobago HDMI AudioDELL S2409WRealtek RTL8111/8168/8411Ubuntu 20.045.4.0-51-generic (x86_64)GNOME Shell 3.36.3X Server 1.20.8modesetting 1.20.8GCC 9.3.0ext41920x10805.9.1-050901-generic (x86_64)GNOME Shell 3.36.44.5 Mesa 20.0.8 (LLVM 10.0.0)5.9.0-050900daily20201021-generic (x86_64)OpenBenchmarking.orgCompiler Details- --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001129Graphics Details- GLAMORJava Details- OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)Python Details- Python 3.8.5Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.4Linux 5.9.1Linux 5.10 GitResult OverviewPhoronix Test Suite100%114%128%141%155%LeelaChessZeroASTC EncoderLevelDBApache CouchDBKeyDBInfluxDBTimed HMMer SearchoneDNNFFTEPyPerformanceGLmark2Stress-NGBRL-CADNeatBenchLuxCoreRender7-Zip Compressiondav1deSpeak-NG Speech EnginelibrsvgSVT-VP9SVT-AV1Tesseract OCRHierarchical INTegrationTNNGROMACSBYTE Unix BenchmarkNAMDBuild2KvazaarMontage Astronomical Image Mosaic EngineBasis UniversalMobile Neural NetworkG'MICC-BloscHuginLibreOfficeTimed Linux Kernel CompilationIncompact3DLAMMPS Molecular Dynamics SimulatorNCNNChaos Group V-RAYTimed Apache CompilationAOM AV1DolfynRNNoiseZstd CompressionYafaRayx265TensorFlow LiteMlpack BenchmarkTimed GDB GNU Debugger CompilationOpenVINORodiniaWebP Image EncodeLibRawTimed MAFFT AlignmentSunflow Rendering SystemOCRMyPDFlibavif avifencRawTherapeeGNU Octave BenchmarkDaCapo BenchmarkCaffeMonte Carlo Simulations of Ionised Nebulae

Ryzen 3 1300Xpyperformance: python_startupstress-ng: NUMAstress-ng: Context Switchingstress-ng: Forkingstress-ng: Semaphoresleveldb: Overwriteleveldb: Overwriteleveldb: Rand Fillleveldb: Rand Fillonednn: Deconvolution Batch deconv_3d - f32 - CPUstress-ng: Socket Activityleveldb: Rand Readstress-ng: MEMFDleveldb: Seq Fillleveldb: Hot Readleveldb: Seq Fillonednn: Recurrent Neural Network Inference - f32 - CPUleveldb: Fill Syncleveldb: Seek Randinfluxdb: 4 - 10000 - 2,5000,1 - 10000stress-ng: CPU Cacheleveldb: Rand Deletencnn: CPU - squeezenetkeydb: couchdb: 100 - 1000 - 24dav1d: Summer Nature 4Kstress-ng: SENDFILEhmmer: Pfam Database Searchonednn: IP Batch 1D - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUffte: N=256, 3D Complex FFT Routineonednn: Deconvolution Batch deconv_1d - f32 - CPUgmic: 2D Function Plotting, 1000 Timessvt-av1: Enc Mode 8 - 1080pinfluxdb: 64 - 10000 - 2,5000,1 - 10000dacapobench: H2ncnn: CPU - yolov4-tinyncnn: CPU - mobilenetglmark2: 1920 x 1080dacapobench: Tradebeansopenvino: Age Gender Recognition Retail 0013 FP16 - CPUkvazaar: Bosphorus 1080p - Mediummlpack: scikit_qdatnn: CPU - MobileNet v2luxcorerender: DLSCbrl-cad: VGR Performance Metricdacapobench: Tradesoapneatbench: CPUmnn: SqueezeNetV1.0compress-7zip: Compress Speed Testluxcorerender: Rainbow Colors and Prismsvt-vp9: VMAF Optimized - Bosphorus 1080popenvino: Age Gender Recognition Retail 0013 FP16 - CPUwebp: Quality 100basis: UASTC Level 2 + RDO Post-Processingrodinia: OpenMP CFD Solverespeak: Text-To-Speech Synthesispyperformance: floatsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pkvazaar: Bosphorus 4K - Very Fastaom-av1: Speed 8 Realtimersvg: SVG Files To PNGopenvino: Age Gender Recognition Retail 0013 FP32 - CPUpyperformance: pathlibmnn: MobileNetV2_224onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUdav1d: Chimera 1080p 10-bitstress-ng: Cryptostress-ng: Glibc C String Functionstesseract-ocr: Time To OCR 7 Imagesonednn: IP Batch All - f32 - CPUkvazaar: Bosphorus 1080p - Ultra Fasthint: FLOATgromacs: Water Benchmarkbyte: Dhrystone 2webp: Quality 100, Lossless, Highest Compressionkvazaar: Bosphorus 1080p - Very Fastnamd: ATPase Simulation - 327,506 Atomsincompact3d: Cylinderdacapobench: Jythonaom-av1: Speed 6 Realtimebuild2: Time To Compilemontage: Mosaic of M17, K band, 1.5 deg x 1.5 degncnn: CPU - vgg16pyperformance: django_templatebasis: ETC1Srodinia: OpenMP Streamclusterdav1d: Summer Nature 1080pblosc: blosclzhugin: Panorama Photo Assistant + Stitching Timesvt-vp9: Visual Quality Optimized - Bosphorus 1080plibreoffice: 20 Documents To PDFkvazaar: Bosphorus 4K - Ultra Fastbuild-linux-kernel: Time To Compiletensorflow-lite: Mobilenet Quantmnn: resnet-v2-50mnn: inception-v3avifenc: 0pyperformance: crypto_pyaesncnn: CPU - googlenetonednn: Recurrent Neural Network Training - f32 - CPUlammps: Rhodopsin Proteinncnn: CPU - alexnettnn: CPU - SqueezeNet v1.1v-ray: CPUmlpack: scikit_icaaom-av1: Speed 4 Two-Passsvt-av1: Enc Mode 4 - 1080ppyperformance: chaosstress-ng: Memory Copyingcompress-zstd: 19pyperformance: nbodybuild-apache: Time To Compilekvazaar: Bosphorus 4K - Mediumyafaray: Total Time For Sample Scenencnn: CPU - resnet50openvino: Age Gender Recognition Retail 0013 FP32 - CPUwebp: Quality 100, Losslessx265: Bosphorus 4Kbasis: UASTC Level 0dolfyn: Computational Fluid Dynamicsrnnoise: webp: Defaultstress-ng: Glibc Qsort Data Sortingpyperformance: regex_compilepyperformance: pickle_pure_pythongmic: Plotting Isosurface Of A 3D Volume, 1000 Timestensorflow-lite: Mobilenet Floatpyperformance: 2to3avifenc: 8mlpack: scikit_svmcaffe: GoogleNet - CPU - 100tensorflow-lite: SqueezeNetastcenc: Thoroughx265: Bosphorus 1080ptensorflow-lite: Inception ResNet V2avifenc: 2caffe: AlexNet - CPU - 200tensorflow-lite: Inception V4compress-zstd: 3ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - resnet18ncnn: CPU - efficientnet-b0avifenc: 10stress-ng: Mallocbuild-gdb: Time To Compilelibraw: Post-Processing Benchmarkncnn: CPU-v2-v2 - mobilenet-v2mlpack: scikit_linearridgeregressiontensorflow-lite: NASNet Mobilepyperformance: json_loadsopenvino: Face Detection 0106 FP32 - CPUmafft: Multiple Sequence Alignment - LSU RNArodinia: OpenMP HotSpot3Dsunflow: Global Illumination + Image Synthesisdav1d: Chimera 1080pstress-ng: Atomicstress-ng: CPU Stressncnn: CPU - mnasnetwebp: Quality 100, Highest Compressionopenvino: Person Detection 0106 FP32 - CPUocrmypdf: Processing 60 Page PDF Documentopenvino: Face Detection 0106 FP16 - CPUstress-ng: Vector Mathcaffe: AlexNet - CPU - 100pyperformance: raytraceastcenc: Mediummnn: mobilenet-v1-1.0rawtherapee: Total Benchmark Timeastcenc: Exhaustivestress-ng: Matrix Mathbasis: UASTC Level 2rodinia: OpenMP Leukocyteoctave-benchmark: openvino: Person Detection 0106 FP16 - CPUcaffe: GoogleNet - CPU - 200rodinia: OpenMP LavaMDgmic: 3D Elevated Function In Rand Colors, 100 Timespyperformance: goopenvino: Person Detection 0106 FP32 - CPUopenvino: Person Detection 0106 FP16 - CPUopenvino: Face Detection 0106 FP32 - CPUopenvino: Face Detection 0106 FP16 - CPUncnn: CPU - blazefacencnn: CPU - shufflenet-v2leveldb: Fill Syncsvt-av1: Enc Mode 0 - 1080paom-av1: Speed 6 Two-Passaom-av1: Speed 0 Two-Passmocassin: Dust 2D tau100.0influxdb: 1024 - 10000 - 2,5000,1 - 10000stress-ng: System V Message Passingstress-ng: MMAPbasis: UASTC Level 3astcenc: Fastlczero: Eigenlczero: BLASLinux 5.4Linux 5.9.1Linux 5.10 Git16.679.55997029.2318307.82316527.2324.917.72617.74924.825.00822650.881.644103.3225.01.66417.666317.4182356.9772.208708303.647.0216.72334.22243083.62203.95057.3046372.01113.76415.226719.175520167.48400764717.5955112.7146.945778544.6384660.7539.21203039971733.597.1383.21290.3850.5031634109917.2014.112162990.5762.252.302.687802.15349.78434.56014063.164.3025.9835.6902.30237.4056.3094256.22849.32368841.3431.745178.99630.84318172818.539260.35037037826.950.74417.656.51693762.243673599110.93340.15996.455103.5073.784.24435.284179.625700.181.37449.979.0147.59282.03130390957.22177.200226.07713431.07864.1972.77325.07286.621387468.081.450.8801481962.4715.315942.6041.60481.60662.621733.3724.4685.1311.74820.57921.8671.78143.1421063424.8222835704358.70722.7311665941950983.8622.005432150134.6399409859875832751.38.4228.0914.067.98015780304.36209.16921.379.286.3830451232.36320.5513.645113.6723.439181.78304850.381214.249.388.4669779.7266.1686312.5522346.764686663913.2110.197110.024678.8816244.7784.291293.2818.3429784.94233077619.23993.0153190.410.410.630.632.156.660.20.0492.350.1631719159.93194317.085.79180.0055.6044143210.864.741178233.4918000.85268049.6522.719.39519.41122.822.46822402.221.81296.7023.31.79418.933314.4032281.3052.374663064.645.3417.53232.48235981.19198.71954.9045502.28118.57814.653219.192220940.10243154716.9767115.0676.754760573.3374659.5738.35207640581765.026.9884.55286.1470.5032221112117.0613.844163920.5761.492.262.721810.93349.18435.06713862.274.2426.2435.3982.2823.37.3186.2514455.70840.19371689.9531.455177.77930.63317966577.688460.35437079861.250.51817.466.53697756.603475595211.04341.21196.963104.4974.284.99334.958177.975649.280.87149.629.0797.57283.74130159156.91376.617225.28113531.22860.8972.76124.97284.573384768.211.460.8771481967.9015.415842.8411.59481.81862.241737.8324.4505.1611.70720.46921.8101.78243.0221063724.8062823234368.73122.6311715841774983.5422.085410167134.3179372159643102753.08.3927.9914.107.95215798673.93208.48321.439.286.3730356032.36320.3913.685113.9803.430182.27304317.831216.729.368.4569760.4366.2986305.7222371.564691863913.2010.182109.877678.5516243.9984.362292.9698.3489777.68232875619.53893.0603190.410.410.630.632.156.660.20.0492.350.163173431597.326.45172.3875.5829328910.867.091199590.6021463.25267417.5822.020.05319.95322.122.88782392.221.79493.7523.11.79919.092294.4922190.1272.376685094.044.3017.72032.60231492.24194.28654.6044414.71118.67314.675318.472320885.86697801017.0364116.4556.744756047.5376159.4038.34207340841727.777.0584.94284.5580.4932279112017.1813.887165930.5661.162.292.680798.86949.05834.93313862.504.2526.3335.2262.3123.37.3126.2313055.54850.35367272.2531.371176.89630.48314508265.629350.35436670538.050.18417.466.46667764.678101593111.00343.56697.400103.6673.584.19434.960178.175652.881.58649.549.0017.53284.22230339856.78576.815224.39613430.99857.8932.78125.15285.268386667.741.450.8741471954.8315.415942.8731.60478.88062.371727.6224.5935.1411.77320.52721.7511.77343.2320963624.7072822614348.74722.7011664841793183.5122.095411013134.0979372359645102761.58.4028.0514.117.97615835328.30209.00421.449.256.3930357832.26301.4413.656114.0053.440181.94304118.871216.919.378.4739764.8566.2836301.0622385.344694163813.1910.187109.948677.9916265.1084.272293.0368.3509786.97232927619.71993.0263190.410.410.630.632.156.660.20.0492.350.1631741400.24269857.666.62172.3558.21283279OpenBenchmarking.org

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupLinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.18, N = 7SE +/- 0.00, N = 3SE +/- 0.03, N = 316.610.810.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupLinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 15.9 / Avg: 16.6 / Max: 16.9Min: 10.8 / Avg: 10.8 / Max: 10.8Min: 10.7 / Avg: 10.77 / Max: 10.8

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: NUMALinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 1.18, N = 3SE +/- 0.31, N = 3SE +/- 0.89, N = 379.5564.7467.091. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMALinux 5.4Linux 5.9.1Linux 5.10 Git1530456075Min: 77.24 / Avg: 79.55 / Max: 81.12Min: 64.15 / Avg: 64.74 / Max: 65.2Min: 66.14 / Avg: 67.09 / Max: 68.881. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingLinux 5.4Linux 5.9.1Linux 5.10 Git300K600K900K1200K1500KSE +/- 1076.78, N = 3SE +/- 8431.86, N = 3SE +/- 12234.48, N = 8997029.231178233.491199590.601. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingLinux 5.4Linux 5.9.1Linux 5.10 Git200K400K600K800K1000KMin: 995106.35 / Avg: 997029.23 / Max: 998830.46Min: 1165490.78 / Avg: 1178233.49 / Max: 1194170.75Min: 1122238.28 / Avg: 1199590.6 / Max: 1232344.941. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: ForkingLinux 5.4Linux 5.9.1Linux 5.10 Git5K10K15K20K25KSE +/- 100.53, N = 3SE +/- 121.43, N = 3SE +/- 32.57, N = 318307.8218000.8521463.251. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: ForkingLinux 5.4Linux 5.9.1Linux 5.10 Git4K8K12K16K20KMin: 18154.7 / Avg: 18307.82 / Max: 18497.24Min: 17763.52 / Avg: 18000.85 / Max: 18164.14Min: 21414.67 / Avg: 21463.25 / Max: 21525.111. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresLinux 5.4Linux 5.9.1Linux 5.10 Git70K140K210K280K350KSE +/- 264.89, N = 3SE +/- 791.14, N = 3SE +/- 70.75, N = 3316527.23268049.65267417.581. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresLinux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KMin: 316199.71 / Avg: 316527.23 / Max: 317051.62Min: 266467.79 / Avg: 268049.65 / Max: 268872.35Min: 267276.25 / Avg: 267417.58 / Max: 267494.061. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.10, N = 3SE +/- 0.38, N = 3SE +/- 0.28, N = 524.922.722.01. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.7 / Avg: 24.9 / Max: 25Min: 22 / Avg: 22.73 / Max: 23.3Min: 21.4 / Avg: 22.02 / Max: 22.81. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.07, N = 3SE +/- 0.32, N = 3SE +/- 0.25, N = 517.7319.4020.051. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 17.65 / Avg: 17.73 / Max: 17.86Min: 18.97 / Avg: 19.4 / Max: 20.02Min: 19.39 / Avg: 20.05 / Max: 20.571. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 317.7519.4119.951. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 17.63 / Avg: 17.75 / Max: 17.98Min: 19.17 / Avg: 19.41 / Max: 19.58Min: 19.67 / Avg: 19.95 / Max: 20.131. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 324.822.822.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.5 / Avg: 24.83 / Max: 25Min: 22.5 / Avg: 22.77 / Max: 23.1Min: 21.9 / Avg: 22.1 / Max: 22.41. (CXX) g++ options: -O3 -lsnappy -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.23, N = 325.0122.4722.89MIN: 22.34MIN: 22.3MIN: 22.271. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.87 / Avg: 25.01 / Max: 25.14Min: 22.42 / Avg: 22.47 / Max: 22.5Min: 22.56 / Avg: 22.89 / Max: 23.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: Socket ActivityLinux 5.4Linux 5.9.1Linux 5.10 Git6001200180024003000SE +/- 35.67, N = 3SE +/- 13.13, N = 3SE +/- 8.33, N = 32650.882402.222392.221. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket ActivityLinux 5.4Linux 5.9.1Linux 5.10 Git5001000150020002500Min: 2580.7 / Avg: 2650.88 / Max: 2697.05Min: 2377.2 / Avg: 2402.22 / Max: 2421.63Min: 2378.87 / Avg: 2392.22 / Max: 2407.541. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadLinux 5.4Linux 5.9.1Linux 5.10 Git0.40770.81541.22311.63082.0385SE +/- 0.001, N = 3SE +/- 0.011, N = 3SE +/- 0.002, N = 31.6441.8121.7941. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 1.64 / Avg: 1.64 / Max: 1.65Min: 1.8 / Avg: 1.81 / Max: 1.83Min: 1.79 / Avg: 1.79 / Max: 1.81. (CXX) g++ options: -O3 -lsnappy -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: MEMFDLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.29, N = 3SE +/- 0.35, N = 3SE +/- 0.42, N = 3103.3296.7093.751. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 102.75 / Avg: 103.32 / Max: 103.67Min: 96.2 / Avg: 96.7 / Max: 97.38Min: 92.96 / Avg: 93.75 / Max: 94.371. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.15, N = 3SE +/- 0.18, N = 3SE +/- 0.30, N = 325.023.323.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.7 / Avg: 25 / Max: 25.2Min: 23 / Avg: 23.27 / Max: 23.6Min: 22.7 / Avg: 23.13 / Max: 23.71. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadLinux 5.4Linux 5.9.1Linux 5.10 Git0.40480.80961.21441.61922.024SE +/- 0.016, N = 3SE +/- 0.018, N = 3SE +/- 0.007, N = 31.6641.7941.7991. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 1.63 / Avg: 1.66 / Max: 1.68Min: 1.76 / Avg: 1.79 / Max: 1.82Min: 1.79 / Avg: 1.8 / Max: 1.811. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.25, N = 317.6718.9319.091. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 17.57 / Avg: 17.67 / Max: 17.85Min: 18.62 / Avg: 18.93 / Max: 19.2Min: 18.62 / Avg: 19.09 / Max: 19.491. (CXX) g++ options: -O3 -lsnappy -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git70140210280350SE +/- 0.98, N = 3SE +/- 0.31, N = 3SE +/- 4.30, N = 15317.42314.40294.49MIN: 312.45MIN: 311.49MIN: 277.971. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git60120180240300Min: 316.36 / Avg: 317.42 / Max: 319.37Min: 314.09 / Avg: 314.4 / Max: 315.02Min: 280.5 / Avg: 294.49 / Max: 314.741. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.4Linux 5.9.1Linux 5.10 Git5001000150020002500SE +/- 64.80, N = 3SE +/- 31.60, N = 3SE +/- 33.13, N = 32356.982281.312190.131. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.4Linux 5.9.1Linux 5.10 Git400800120016002000Min: 2257.09 / Avg: 2356.98 / Max: 2478.43Min: 2224.81 / Avg: 2281.31 / Max: 2334.09Min: 2127.01 / Avg: 2190.13 / Max: 2239.161. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomLinux 5.4Linux 5.9.1Linux 5.10 Git0.53461.06921.60382.13842.673SE +/- 0.030, N = 3SE +/- 0.005, N = 3SE +/- 0.009, N = 32.2082.3742.3761. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.18 / Avg: 2.21 / Max: 2.27Min: 2.37 / Avg: 2.37 / Max: 2.38Min: 2.36 / Avg: 2.38 / Max: 2.391. (CXX) g++ options: -O3 -lsnappy -lpthread

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.9.1Linux 5.10 Git150K300K450K600K750KSE +/- 7077.48, N = 3SE +/- 9563.32, N = 4SE +/- 1457.21, N = 3708303.6663064.6685094.0
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.9.1Linux 5.10 Git120K240K360K480K600KMin: 694273.3 / Avg: 708303.63 / Max: 716941.9Min: 639495.1 / Avg: 663064.6 / Max: 685868.5Min: 682547.7 / Avg: 685094 / Max: 687595

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 CacheLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455SE +/- 0.65, N = 4SE +/- 0.49, N = 7SE +/- 0.25, N = 347.0245.3444.301. (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 CacheLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050Min: 45.4 / Avg: 47.02 / Max: 48.43Min: 42.7 / Avg: 45.34 / Max: 46.57Min: 44 / Avg: 44.3 / Max: 44.791. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteLinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.20, N = 316.7217.5317.721. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteLinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 16.57 / Avg: 16.72 / Max: 16.85Min: 17.44 / Avg: 17.53 / Max: 17.65Min: 17.31 / Avg: 17.72 / Max: 17.941. (CXX) g++ options: -O3 -lsnappy -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 20200916Target: CPU - Model: squeezenetLinux 5.4Linux 5.9.1Linux 5.10 Git816243240SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 334.2232.4832.60MIN: 31.98 / MAX: 75.66MIN: 32.02 / MAX: 54.08MIN: 32.06 / MAX: 74.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 34.05 / Avg: 34.22 / Max: 34.34Min: 32.34 / Avg: 32.48 / Max: 32.71Min: 32.45 / Avg: 32.6 / Max: 32.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

KeyDB

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

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16Linux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KSE +/- 589.73, N = 3SE +/- 1004.66, N = 3SE +/- 1736.74, N = 3243083.62235981.19231492.241. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16Linux 5.4Linux 5.9.1Linux 5.10 Git40K80K120K160K200KMin: 241913.09 / Avg: 243083.62 / Max: 243794.35Min: 234733.44 / Avg: 235981.19 / Max: 237969.02Min: 228770.14 / Avg: 231492.24 / Max: 234721.841. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Apache CouchDB

This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 24Linux 5.4Linux 5.9.1Linux 5.10 Git4080120160200SE +/- 0.82, N = 3SE +/- 0.73, N = 3SE +/- 1.38, N = 3203.95198.72194.291. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 24Linux 5.4Linux 5.9.1Linux 5.10 Git4080120160200Min: 202.39 / Avg: 203.95 / Max: 205.18Min: 197.6 / Avg: 198.72 / Max: 200.1Min: 191.93 / Avg: 194.29 / Max: 196.721. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

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 0.7.0Video Input: Summer Nature 4KLinux 5.4Linux 5.9.1Linux 5.10 Git1326395265SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 357.3054.9054.60MIN: 54.02 / MAX: 63.6MIN: 51.84 / MAX: 60.87MIN: 51.53 / MAX: 60.821. (CC) gcc options: -pthread -ldl -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455Min: 57.01 / Avg: 57.3 / Max: 57.55Min: 54.79 / Avg: 54.9 / Max: 54.96Min: 54.53 / Avg: 54.6 / Max: 54.691. (CC) gcc options: -pthread -ldl -lm

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: SENDFILELinux 5.4Linux 5.9.1Linux 5.10 Git10K20K30K40K50KSE +/- 17.45, N = 3SE +/- 32.82, N = 3SE +/- 11.53, N = 346372.0145502.2844414.711. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILELinux 5.4Linux 5.9.1Linux 5.10 Git8K16K24K32K40KMin: 46351.4 / Avg: 46372.01 / Max: 46406.7Min: 45454.23 / Avg: 45502.28 / Max: 45565.04Min: 44397.5 / Avg: 44414.71 / Max: 44436.61. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.12, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 3113.76118.58118.671. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 113.53 / Avg: 113.76 / Max: 113.9Min: 118.26 / Avg: 118.58 / Max: 119.06Min: 118.43 / Avg: 118.67 / Max: 119.011. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 315.2314.6514.68MIN: 14.54MIN: 14.53MIN: 14.551. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 15.15 / Avg: 15.23 / Max: 15.35Min: 14.65 / Avg: 14.65 / Max: 14.66Min: 14.63 / Avg: 14.68 / Max: 14.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 319.1819.1918.47MIN: 18.1MIN: 18.15MIN: 17.991. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 19.06 / Avg: 19.18 / Max: 19.26Min: 19.17 / Avg: 19.19 / Max: 19.21Min: 18.36 / Avg: 18.47 / Max: 18.631. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 RoutineLinux 5.4Linux 5.9.1Linux 5.10 Git4K8K12K16K20KSE +/- 70.01, N = 3SE +/- 168.74, N = 3SE +/- 203.21, N = 320167.4820940.1020885.871. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineLinux 5.4Linux 5.9.1Linux 5.10 Git4K8K12K16K20KMin: 20027.46 / Avg: 20167.48 / Max: 20237.52Min: 20602.77 / Avg: 20940.1 / Max: 21117.56Min: 20481.25 / Avg: 20885.87 / Max: 21121.321. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 317.6016.9817.04MIN: 16.38MIN: 16.48MIN: 16.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 17.37 / Avg: 17.6 / Max: 17.71Min: 16.85 / Avg: 16.98 / Max: 17.13Min: 17.01 / Avg: 17.04 / Max: 17.081. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.56, N = 3SE +/- 0.52, N = 3SE +/- 0.31, N = 3112.71115.07116.461. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 111.6 / Avg: 112.71 / Max: 113.44Min: 114.15 / Avg: 115.07 / Max: 115.97Min: 115.83 / Avg: 116.46 / Max: 116.831. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.008, N = 3SE +/- 0.006, N = 3SE +/- 0.006, N = 36.9456.7546.7441. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 6.93 / Avg: 6.94 / Max: 6.96Min: 6.74 / Avg: 6.75 / Max: 6.76Min: 6.73 / Avg: 6.74 / Max: 6.751. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.9.1Linux 5.10 Git200K400K600K800K1000KSE +/- 2206.20, N = 3SE +/- 1650.52, N = 3SE +/- 3404.87, N = 3778544.6760573.3756047.5
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.9.1Linux 5.10 Git130K260K390K520K650KMin: 776317.6 / Avg: 778544.57 / Max: 782956.9Min: 758419.4 / Avg: 760573.27 / Max: 763816.6Min: 749939.1 / Avg: 756047.53 / Max: 761708.4

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: H2Linux 5.4Linux 5.9.1Linux 5.10 Git8001600240032004000SE +/- 33.88, N = 20SE +/- 44.95, N = 20SE +/- 45.67, N = 20384637463761
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Linux 5.4Linux 5.9.1Linux 5.10 Git7001400210028003500Min: 3547 / Avg: 3845.5 / Max: 4116Min: 3431 / Avg: 3745.9 / Max: 4250Min: 3427 / Avg: 3760.85 / Max: 4149

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 20200916Target: CPU - Model: yolov4-tinyLinux 5.4Linux 5.9.1Linux 5.10 Git1428425670SE +/- 0.31, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 360.7559.5759.40MIN: 51.09 / MAX: 134.68MIN: 51.51 / MAX: 66.18MIN: 51.27 / MAX: 86.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyLinux 5.4Linux 5.9.1Linux 5.10 Git1224364860Min: 60.23 / Avg: 60.75 / Max: 61.29Min: 59.42 / Avg: 59.57 / Max: 59.83Min: 59.04 / Avg: 59.4 / Max: 59.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetLinux 5.4Linux 5.9.1Linux 5.10 Git918273645SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 339.2138.3538.34MIN: 37.49 / MAX: 71.54MIN: 36.8 / MAX: 56.64MIN: 36.65 / MAX: 42.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetLinux 5.4Linux 5.9.1Linux 5.10 Git816243240Min: 38.96 / Avg: 39.21 / Max: 39.39Min: 38.07 / Avg: 38.35 / Max: 38.52Min: 38.24 / Avg: 38.34 / Max: 38.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: 1920 x 1080Linux 5.4Linux 5.9.1Linux 5.10 Git400800120016002000203020762073

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: TradebeansLinux 5.4Linux 5.9.1Linux 5.10 Git9001800270036004500SE +/- 22.41, N = 4SE +/- 32.31, N = 20SE +/- 44.30, N = 20399740584084
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansLinux 5.4Linux 5.9.1Linux 5.10 Git7001400210028003500Min: 3939 / Avg: 3996.5 / Max: 4039Min: 3798 / Avg: 4058.2 / Max: 4350Min: 3754 / Avg: 4084.45 / Max: 4561

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git400800120016002000SE +/- 1.79, N = 3SE +/- 22.73, N = 3SE +/- 13.14, N = 31733.591765.021727.77
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git30060090012001500Min: 1730.41 / Avg: 1733.59 / Max: 1736.59Min: 1737.29 / Avg: 1765.02 / Max: 1810.08Min: 1714.54 / Avg: 1727.77 / Max: 1754.05

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 1080p - Video Preset: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 37.136.987.051. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 7.13 / Avg: 7.13 / Max: 7.14Min: 6.85 / Avg: 6.98 / Max: 7.06Min: 7.04 / Avg: 7.05 / Max: 7.061. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 0.29, N = 383.2184.5584.94
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaLinux 5.4Linux 5.9.1Linux 5.10 Git1632486480Min: 82.86 / Avg: 83.21 / Max: 83.47Min: 84.06 / Avg: 84.55 / Max: 84.97Min: 84.36 / Avg: 84.94 / Max: 85.3

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 v2Linux 5.4Linux 5.9.1Linux 5.10 Git60120180240300SE +/- 0.19, N = 3SE +/- 0.78, N = 3SE +/- 0.05, N = 3290.39286.15284.56MIN: 286.11 / MAX: 306.89MIN: 284.14 / MAX: 303.22MIN: 283.86 / MAX: 286.191. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2Linux 5.4Linux 5.9.1Linux 5.10 Git50100150200250Min: 290.07 / Avg: 290.39 / Max: 290.72Min: 284.8 / Avg: 286.15 / Max: 287.51Min: 284.48 / Avg: 284.56 / Max: 284.641. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCLinux 5.4Linux 5.9.1Linux 5.10 Git0.11250.2250.33750.450.5625SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.500.500.49MIN: 0.49MIN: 0.49MIN: 0.48 / MAX: 0.5
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 0.5 / Avg: 0.5 / Max: 0.5Min: 0.5 / Avg: 0.5 / Max: 0.5Min: 0.49 / Avg: 0.49 / Max: 0.5

BRL-CAD

BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance MetricLinux 5.4Linux 5.9.1Linux 5.10 Git7K14K21K28K35K3163432221322791. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lpthread -ldl -luuid -lm

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: TradesoapLinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KSE +/- 134.21, N = 6SE +/- 159.15, N = 4SE +/- 101.79, N = 4109911121111201
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapLinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KMin: 10518 / Avg: 10990.83 / Max: 11426Min: 10752 / Avg: 11210.75 / Max: 11484Min: 10949 / Avg: 11201 / Max: 11437

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: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 37.207.067.18
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPULinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 7.18 / Avg: 7.2 / Max: 7.22Min: 7.03 / Avg: 7.06 / Max: 7.11Min: 7.13 / Avg: 7.18 / Max: 7.23

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 2020-09-17Model: SqueezeNetV1.0Linux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 314.1113.8413.89MIN: 13.83 / MAX: 17.93MIN: 13.75 / MAX: 15.88MIN: 13.77 / MAX: 16.561. (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 2020-09-17Model: SqueezeNetV1.0Linux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 13.95 / Avg: 14.11 / Max: 14.27Min: 13.83 / Avg: 13.84 / Max: 13.87Min: 13.87 / Avg: 13.89 / Max: 13.91. (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

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 TestLinux 5.4Linux 5.9.1Linux 5.10 Git4K8K12K16K20KSE +/- 251.42, N = 3SE +/- 227.49, N = 3SE +/- 45.86, N = 31629916392165931. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestLinux 5.4Linux 5.9.1Linux 5.10 Git3K6K9K12K15KMin: 15802 / Avg: 16298.67 / Max: 16615Min: 15945 / Avg: 16391.67 / Max: 16690Min: 16501 / Avg: 16592.67 / Max: 166411. (CXX) g++ options: -pipe -lpthread

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismLinux 5.4Linux 5.9.1Linux 5.10 Git0.12830.25660.38490.51320.6415SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.570.570.56MIN: 0.55 / MAX: 0.64MIN: 0.55 / MAX: 0.65MIN: 0.54 / MAX: 0.64
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.57 / Avg: 0.57 / Max: 0.58Min: 0.56 / Avg: 0.56 / Max: 0.57

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: VMAF Optimized - Input: Bosphorus 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1428425670SE +/- 0.78, N = 3SE +/- 0.72, N = 3SE +/- 0.69, N = 362.2561.4961.161. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1224364860Min: 60.69 / Avg: 62.25 / Max: 63.08Min: 60.19 / Avg: 61.49 / Max: 62.68Min: 59.79 / Avg: 61.16 / Max: 61.951. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.51751.0351.55252.072.5875SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 32.302.262.29
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.28 / Avg: 2.3 / Max: 2.32Min: 2.19 / Avg: 2.26 / Max: 2.3Min: 2.22 / Avg: 2.29 / Max: 2.32

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 100Linux 5.4Linux 5.9.1Linux 5.10 Git0.61221.22441.83662.44883.061SE +/- 0.011, N = 3SE +/- 0.014, N = 3SE +/- 0.001, N = 32.6872.7212.6801. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100Linux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.68 / Avg: 2.69 / Max: 2.71Min: 2.71 / Avg: 2.72 / Max: 2.75Min: 2.68 / Avg: 2.68 / Max: 2.681. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingLinux 5.4Linux 5.9.1Linux 5.10 Git2004006008001000SE +/- 1.87, N = 3SE +/- 0.55, N = 3SE +/- 1.47, N = 3802.15810.93798.871. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingLinux 5.4Linux 5.9.1Linux 5.10 Git140280420560700Min: 799.47 / Avg: 802.15 / Max: 805.76Min: 809.85 / Avg: 810.93 / Max: 811.61Min: 796.55 / Avg: 798.87 / Max: 801.581. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 349.7849.1849.061. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050Min: 49.69 / Avg: 49.78 / Max: 49.92Min: 49.01 / Avg: 49.18 / Max: 49.46Min: 48.92 / Avg: 49.06 / Max: 49.21. (CXX) g++ options: -O2 -lOpenCL

eSpeak-NG Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. This test profile is now tracking the eSpeak-NG version of eSpeak. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisLinux 5.4Linux 5.9.1Linux 5.10 Git816243240SE +/- 0.28, N = 4SE +/- 0.07, N = 4SE +/- 0.36, N = 434.5635.0734.931. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 33.99 / Avg: 34.56 / Max: 35.08Min: 34.94 / Avg: 35.07 / Max: 35.22Min: 34.06 / Avg: 34.93 / Max: 35.811. (CC) gcc options: -O2 -std=c99

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.58, N = 3140138138
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 139 / Avg: 140 / Max: 141

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 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1428425670SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.25, N = 363.1662.2762.501. (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 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1224364860Min: 62.95 / Avg: 63.16 / Max: 63.32Min: 61.96 / Avg: 62.27 / Max: 62.46Min: 62.25 / Avg: 62.5 / Max: 62.991. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 FastLinux 5.4Linux 5.9.1Linux 5.10 Git0.96751.9352.90253.874.8375SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.304.244.251. (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 FastLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 4.29 / Avg: 4.3 / Max: 4.31Min: 4.24 / Avg: 4.24 / Max: 4.25Min: 4.24 / Avg: 4.25 / Max: 4.261. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 RealtimeLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 325.9826.2426.331. (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 RealtimeLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 25.97 / Avg: 25.98 / Max: 26Min: 26.13 / Avg: 26.24 / Max: 26.33Min: 26.26 / Avg: 26.33 / Max: 26.381. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

librsvg

RSVG/librsvg is an SVG vector graphics library. This test profile times how long it takes to complete various operations by rsvg-convert. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGLinux 5.4Linux 5.9.1Linux 5.10 Git816243240SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 335.6935.4035.231. rsvg-convert version 2.48.7
OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGLinux 5.4Linux 5.9.1Linux 5.10 Git816243240Min: 35.57 / Avg: 35.69 / Max: 35.85Min: 35.18 / Avg: 35.4 / Max: 35.61Min: 35.03 / Avg: 35.23 / Max: 35.571. rsvg-convert version 2.48.7

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.51981.03961.55942.07922.599SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 32.302.282.31
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.29 / Avg: 2.3 / Max: 2.31Min: 2.21 / Avg: 2.28 / Max: 2.31Min: 2.29 / Avg: 2.31 / Max: 2.32

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 323.023.323.3
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 23.2 / Avg: 23.27 / Max: 23.3Min: 23.3 / Avg: 23.33 / Max: 23.4

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 2020-09-17Model: MobileNetV2_224Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.006, N = 3SE +/- 0.029, N = 3SE +/- 0.040, N = 37.4057.3187.312MIN: 7.31 / MAX: 9.26MIN: 7.21 / MAX: 20.3MIN: 7.17 / MAX: 19.451. (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 2020-09-17Model: MobileNetV2_224Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 7.4 / Avg: 7.41 / Max: 7.42Min: 7.26 / Avg: 7.32 / Max: 7.36Min: 7.23 / Avg: 7.31 / Max: 7.351. (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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.01857, N = 3SE +/- 0.00318, N = 3SE +/- 0.00698, N = 36.309426.251446.23130MIN: 6.12MIN: 6.11MIN: 6.11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 6.28 / Avg: 6.31 / Max: 6.34Min: 6.25 / Avg: 6.25 / Max: 6.26Min: 6.22 / Avg: 6.23 / Max: 6.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 0.7.0Video Input: Chimera 1080p 10-bitLinux 5.4Linux 5.9.1Linux 5.10 Git1326395265SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 356.2255.7055.54MIN: 38.47 / MAX: 125.61MIN: 38.1 / MAX: 122.2MIN: 38.02 / MAX: 121.841. (CC) gcc options: -pthread -ldl -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455Min: 56.09 / Avg: 56.22 / Max: 56.29Min: 55.43 / Avg: 55.7 / Max: 55.85Min: 55.47 / Avg: 55.54 / Max: 55.651. (CC) gcc options: -pthread -ldl -lm

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: CryptoLinux 5.4Linux 5.9.1Linux 5.10 Git2004006008001000SE +/- 1.37, N = 3SE +/- 10.46, N = 3SE +/- 1.06, N = 3849.32840.19850.351. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoLinux 5.4Linux 5.9.1Linux 5.10 Git150300450600750Min: 846.59 / Avg: 849.32 / Max: 850.97Min: 819.41 / Avg: 840.19 / Max: 852.71Min: 848.6 / Avg: 850.35 / Max: 852.251. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsLinux 5.4Linux 5.9.1Linux 5.10 Git80K160K240K320K400KSE +/- 1206.75, N = 3SE +/- 2534.78, N = 3SE +/- 5072.23, N = 3368841.34371689.95367272.251. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsLinux 5.4Linux 5.9.1Linux 5.10 Git60K120K180K240K300KMin: 367088.91 / Avg: 368841.34 / Max: 371154.74Min: 368857.66 / Avg: 371689.95 / Max: 376747.37Min: 359338.45 / Avg: 367272.25 / Max: 376713.961. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 ImagesLinux 5.4Linux 5.9.1Linux 5.10 Git714212835SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 331.7531.4631.37
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 31.64 / Avg: 31.74 / Max: 31.88Min: 31.37 / Avg: 31.46 / Max: 31.59Min: 31.23 / Avg: 31.37 / Max: 31.51

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git4080120160200SE +/- 0.45, N = 3SE +/- 0.65, N = 3SE +/- 0.33, N = 3179.00177.78176.90MIN: 174.85MIN: 174.79MIN: 174.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 178.18 / Avg: 179 / Max: 179.72Min: 177.02 / Avg: 177.78 / Max: 179.08Min: 176.37 / Avg: 176.9 / Max: 177.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 1080p - Video Preset: Ultra FastLinux 5.4Linux 5.9.1Linux 5.10 Git714212835SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 330.8430.6330.481. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra FastLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 30.77 / Avg: 30.84 / Max: 30.94Min: 30.58 / Avg: 30.63 / Max: 30.69Min: 30.36 / Avg: 30.48 / Max: 30.571. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATLinux 5.4Linux 5.9.1Linux 5.10 Git70M140M210M280M350MSE +/- 1439352.37, N = 3SE +/- 2419757.91, N = 3SE +/- 806993.23, N = 3318172818.54317966577.69314508265.631. (CC) gcc options: -O3 -march=native -lm
OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATLinux 5.4Linux 5.9.1Linux 5.10 Git60M120M180M240M300MMin: 316602924.07 / Avg: 318172818.54 / Max: 321047449.79Min: 314523559.06 / Avg: 317966577.69 / Max: 322633405.68Min: 313660017.77 / Avg: 314508265.63 / Max: 316121536.691. (CC) gcc options: -O3 -march=native -lm

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 BenchmarkLinux 5.4Linux 5.9.1Linux 5.10 Git0.07970.15940.23910.31880.3985SE +/- 0.003, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.3500.3540.3541. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkLinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.35 / Avg: 0.35 / Max: 0.35Min: 0.35 / Avg: 0.35 / Max: 0.35Min: 0.35 / Avg: 0.35 / Max: 0.351. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2Linux 5.4Linux 5.9.1Linux 5.10 Git8M16M24M32M40MSE +/- 135904.30, N = 3SE +/- 103791.21, N = 3SE +/- 134932.02, N = 337037826.937079861.236670538.0
OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2Linux 5.4Linux 5.9.1Linux 5.10 Git6M12M18M24M30MMin: 36766888.7 / Avg: 37037826.87 / Max: 37192119.2Min: 36924685.8 / Avg: 37079861.23 / Max: 37276857Min: 36411707.5 / Avg: 36670538.03 / Max: 36866097.2

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 CompressionLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455SE +/- 0.22, N = 3SE +/- 0.19, N = 3SE +/- 0.13, N = 350.7450.5250.181. (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 CompressionLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050Min: 50.38 / Avg: 50.74 / Max: 51.13Min: 50.22 / Avg: 50.52 / Max: 50.87Min: 50.02 / Avg: 50.18 / Max: 50.441. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 1080p - Video Preset: Very FastLinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 317.6517.4617.461. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very FastLinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 17.63 / Avg: 17.65 / Max: 17.67Min: 17.41 / Avg: 17.46 / Max: 17.57Min: 17.35 / Avg: 17.46 / Max: 17.61. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 AtomsLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.00779, N = 3SE +/- 0.01168, N = 3SE +/- 0.00817, N = 36.516936.536976.46667
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 6.51 / Avg: 6.52 / Max: 6.53Min: 6.52 / Avg: 6.54 / Max: 6.56Min: 6.45 / Avg: 6.47 / Max: 6.48

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: CylinderLinux 5.4Linux 5.9.1Linux 5.10 Git160320480640800SE +/- 5.06, N = 3SE +/- 5.32, N = 3SE +/- 11.35, N = 3762.24756.60764.681. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: CylinderLinux 5.4Linux 5.9.1Linux 5.10 Git130260390520650Min: 752.2 / Avg: 762.24 / Max: 768.24Min: 749.96 / Avg: 756.6 / Max: 767.13Min: 744.16 / Avg: 764.68 / Max: 783.361. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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: JythonLinux 5.4Linux 5.9.1Linux 5.10 Git13002600390052006500SE +/- 34.33, N = 4SE +/- 32.95, N = 4SE +/- 33.59, N = 4599159525931
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonLinux 5.4Linux 5.9.1Linux 5.10 Git10002000300040005000Min: 5908 / Avg: 5991 / Max: 6059Min: 5871 / Avg: 5951.75 / Max: 6024Min: 5862 / Avg: 5930.5 / Max: 6023

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 RealtimeLinux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 310.9311.0411.001. (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 RealtimeLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 10.9 / Avg: 10.93 / Max: 10.98Min: 10.97 / Avg: 11.04 / Max: 11.13Min: 10.9 / Avg: 11 / Max: 11.121. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 0.12Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git70140210280350SE +/- 0.57, N = 3SE +/- 0.95, N = 3SE +/- 1.32, N = 3340.16341.21343.57
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git60120180240300Min: 339.41 / Avg: 340.16 / Max: 341.29Min: 339.44 / Avg: 341.21 / Max: 342.68Min: 341.22 / Avg: 343.57 / Max: 345.78

Montage Astronomical Image Mosaic Engine

Montage is an open-source astronomical image mosaic engine. This BSD-licensed astronomy software is developed by the California Institute of Technology, Pasadena. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMontage Astronomical Image Mosaic Engine 6.0Mosaic of M17, K band, 1.5 deg x 1.5 degLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 396.4696.9697.401. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterMontage Astronomical Image Mosaic Engine 6.0Mosaic of M17, K band, 1.5 deg x 1.5 degLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 96.39 / Avg: 96.45 / Max: 96.53Min: 96.63 / Avg: 96.96 / Max: 97.23Min: 97.11 / Avg: 97.4 / Max: 97.851. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2

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 20200916Target: CPU - Model: vgg16Linux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3103.50104.49103.66MIN: 101.62 / MAX: 131.33MIN: 103.46 / MAX: 108.77MIN: 102.68 / MAX: 107.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16Linux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 103.42 / Avg: 103.5 / Max: 103.56Min: 104.44 / Avg: 104.49 / Max: 104.53Min: 103.5 / Avg: 103.66 / Max: 103.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateLinux 5.4Linux 5.9.1Linux 5.10 Git1632486480SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 373.774.273.5
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateLinux 5.4Linux 5.9.1Linux 5.10 Git1428425670Min: 73.6 / Avg: 73.67 / Max: 73.7Min: 74.1 / Avg: 74.17 / Max: 74.3Min: 73.5 / Avg: 73.53 / Max: 73.6

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1SLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.09, N = 3SE +/- 0.94, N = 3SE +/- 0.21, N = 384.2484.9984.191. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1SLinux 5.4Linux 5.9.1Linux 5.10 Git1632486480Min: 84.1 / Avg: 84.24 / Max: 84.42Min: 83.94 / Avg: 84.99 / Max: 86.87Min: 83.97 / Avg: 84.19 / Max: 84.611. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterLinux 5.4Linux 5.9.1Linux 5.10 Git816243240SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 335.2834.9634.961. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterLinux 5.4Linux 5.9.1Linux 5.10 Git816243240Min: 35.13 / Avg: 35.28 / Max: 35.41Min: 34.87 / Avg: 34.96 / Max: 35.03Min: 34.93 / Avg: 34.96 / Max: 351. (CXX) g++ options: -O2 -lOpenCL

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git4080120160200SE +/- 0.27, N = 3SE +/- 0.05, N = 3SE +/- 0.38, N = 3179.62177.97178.17MIN: 160.18 / MAX: 194.51MIN: 158.4 / MAX: 192.29MIN: 162.42 / MAX: 193.211. (CC) gcc options: -pthread -ldl -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 179.12 / Avg: 179.62 / Max: 180.04Min: 177.86 / Avg: 177.97 / Max: 178.04Min: 177.65 / Avg: 178.17 / Max: 178.911. (CC) gcc options: -pthread -ldl -lm

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: blosclzLinux 5.4Linux 5.9.1Linux 5.10 Git12002400360048006000SE +/- 12.96, N = 3SE +/- 35.24, N = 3SE +/- 27.44, N = 35700.15649.25652.81. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzLinux 5.4Linux 5.9.1Linux 5.10 Git10002000300040005000Min: 5674.2 / Avg: 5700.07 / Max: 5714.5Min: 5606 / Avg: 5649.17 / Max: 5719Min: 5598.2 / Avg: 5652.8 / Max: 5684.91. (CXX) g++ options: -rdynamic

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 TimeLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.21, N = 3SE +/- 0.75, N = 3SE +/- 0.58, N = 381.3780.8781.59
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeLinux 5.4Linux 5.9.1Linux 5.10 Git1632486480Min: 81.05 / Avg: 81.37 / Max: 81.76Min: 79.37 / Avg: 80.87 / Max: 81.7Min: 80.51 / Avg: 81.59 / Max: 82.49

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 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1122334455SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.12, N = 349.9749.6249.541. (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 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050Min: 49.8 / Avg: 49.97 / Max: 50.13Min: 49.32 / Avg: 49.62 / Max: 50.01Min: 49.32 / Avg: 49.54 / Max: 49.741. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

LibreOffice

Various benchmarking operations with the LibreOffice open-source office suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDFLinux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.083, N = 24SE +/- 0.074, N = 25SE +/- 0.078, N = 259.0149.0799.0011. LibreOffice 6.4.6.2 40(Build:2)
OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDFLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 8.83 / Avg: 9.01 / Max: 10.89Min: 8.81 / Avg: 9.08 / Max: 10.77Min: 8.78 / Avg: 9 / Max: 10.831. LibreOffice 6.4.6.2 40(Build:2)

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 FastLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 37.597.577.531. (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 FastLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 7.59 / Avg: 7.59 / Max: 7.6Min: 7.56 / Avg: 7.57 / Max: 7.58Min: 7.53 / Avg: 7.53 / Max: 7.541. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 CompileLinux 5.4Linux 5.9.1Linux 5.10 Git60120180240300SE +/- 0.79, N = 3SE +/- 0.86, N = 3SE +/- 0.83, N = 3282.03283.74284.22
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git50100150200250Min: 281.22 / Avg: 282.03 / Max: 283.61Min: 282.87 / Avg: 283.74 / Max: 285.47Min: 283.28 / Avg: 284.22 / Max: 285.89

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 QuantLinux 5.4Linux 5.9.1Linux 5.10 Git70K140K210K280K350KSE +/- 1091.25, N = 3SE +/- 52.86, N = 3SE +/- 288.83, N = 3303909301591303398
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantLinux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KMin: 302594 / Avg: 303909 / Max: 306075Min: 301501 / Avg: 301590.67 / Max: 301684Min: 302820 / Avg: 303397.67 / Max: 303687

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 2020-09-17Model: resnet-v2-50Linux 5.4Linux 5.9.1Linux 5.10 Git1326395265SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 357.2256.9156.79MIN: 56.58 / MAX: 159.3MIN: 56.33 / MAX: 109.46MIN: 56.21 / MAX: 781. (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 2020-09-17Model: resnet-v2-50Linux 5.4Linux 5.9.1Linux 5.10 Git1122334455Min: 57.05 / Avg: 57.22 / Max: 57.55Min: 56.81 / Avg: 56.91 / Max: 57Min: 56.69 / Avg: 56.79 / Max: 56.851. (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 2020-09-17Model: inception-v3Linux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.43, N = 377.2076.6276.82MIN: 76.5 / MAX: 134.4MIN: 75.63 / MAX: 89.84MIN: 75.8 / MAX: 89.671. (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 2020-09-17Model: inception-v3Linux 5.4Linux 5.9.1Linux 5.10 Git1530456075Min: 77.09 / Avg: 77.2 / Max: 77.4Min: 76.02 / Avg: 76.62 / Max: 77.06Min: 75.99 / Avg: 76.82 / Max: 77.431. (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

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: 0Linux 5.4Linux 5.9.1Linux 5.10 Git50100150200250SE +/- 0.82, N = 3SE +/- 0.37, N = 3SE +/- 0.50, N = 3226.08225.28224.401. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0Linux 5.4Linux 5.9.1Linux 5.10 Git4080120160200Min: 224.82 / Avg: 226.08 / Max: 227.62Min: 224.8 / Avg: 225.28 / Max: 226.01Min: 223.51 / Avg: 224.4 / Max: 225.231. (CXX) g++ options: -O3 -fPIC

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.33, N = 3134135134
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 133 / Avg: 133.67 / Max: 134

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 20200916Target: CPU - Model: googlenetLinux 5.4Linux 5.9.1Linux 5.10 Git714212835SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 331.0731.2230.99MIN: 30.38 / MAX: 45.48MIN: 30.48 / MAX: 123.81MIN: 30.42 / MAX: 51.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 30.91 / Avg: 31.07 / Max: 31.27Min: 30.99 / Avg: 31.22 / Max: 31.65Min: 30.95 / Avg: 30.99 / Max: 31.021. (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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git2004006008001000SE +/- 0.37, N = 3SE +/- 3.07, N = 3SE +/- 2.31, N = 3864.20860.90857.89MIN: 858.95MIN: 855.4MIN: 853.431. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPULinux 5.4Linux 5.9.1Linux 5.10 Git150300450600750Min: 863.46 / Avg: 864.2 / Max: 864.57Min: 857.2 / Avg: 860.9 / Max: 867Min: 854.19 / Avg: 857.89 / Max: 862.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinLinux 5.4Linux 5.9.1Linux 5.10 Git0.62571.25141.87712.50283.1285SE +/- 0.016, N = 3SE +/- 0.012, N = 3SE +/- 0.012, N = 32.7732.7612.7811. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.75 / Avg: 2.77 / Max: 2.8Min: 2.74 / Avg: 2.76 / Max: 2.78Min: 2.76 / Avg: 2.78 / Max: 2.791. (CXX) g++ options: -O3 -pthread -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 20200916Target: CPU - Model: alexnetLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 325.0724.9725.15MIN: 24.46 / MAX: 33.02MIN: 24.62 / MAX: 36.03MIN: 24.71 / MAX: 35.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.99 / Avg: 25.07 / Max: 25.16Min: 24.94 / Avg: 24.97 / Max: 25.01Min: 25.12 / Avg: 25.15 / Max: 25.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 v1.1Linux 5.4Linux 5.9.1Linux 5.10 Git60120180240300SE +/- 1.09, N = 3SE +/- 0.83, N = 3SE +/- 1.35, N = 3286.62284.57285.27MIN: 283.98 / MAX: 293.92MIN: 282.82 / MAX: 287.26MIN: 282.05 / MAX: 288.021. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Linux 5.4Linux 5.9.1Linux 5.10 Git50100150200250Min: 284.46 / Avg: 286.62 / Max: 287.95Min: 283.52 / Avg: 284.57 / Max: 286.2Min: 282.58 / Avg: 285.27 / Max: 286.711. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

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: CPULinux 5.4Linux 5.9.1Linux 5.10 Git8001600240032004000SE +/- 14.43, N = 3SE +/- 5.67, N = 3SE +/- 16.67, N = 3387438473866
OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPULinux 5.4Linux 5.9.1Linux 5.10 Git7001400210028003500Min: 3849 / Avg: 3874 / Max: 3899Min: 3841 / Avg: 3846.67 / Max: 3858Min: 3849 / Avg: 3865.67 / Max: 3899

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaLinux 5.4Linux 5.9.1Linux 5.10 Git1530456075SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.13, N = 368.0868.2167.74
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaLinux 5.4Linux 5.9.1Linux 5.10 Git1326395265Min: 67.94 / Avg: 68.08 / Max: 68.28Min: 68.03 / Avg: 68.21 / Max: 68.56Min: 67.55 / Avg: 67.74 / Max: 67.99

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 4 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git0.32850.6570.98551.3141.6425SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.451.461.451. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 1.45 / Avg: 1.45 / Max: 1.46Min: 1.45 / Avg: 1.46 / Max: 1.46Min: 1.45 / Avg: 1.45 / Max: 1.461. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git0.1980.3960.5940.7920.99SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 30.8800.8770.8741. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 0.88 / Avg: 0.88 / Max: 0.88Min: 0.88 / Avg: 0.88 / Max: 0.88Min: 0.87 / Avg: 0.87 / Max: 0.881. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150148148147

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: Memory CopyingLinux 5.4Linux 5.9.1Linux 5.10 Git400800120016002000SE +/- 10.71, N = 3SE +/- 6.52, N = 3SE +/- 16.66, N = 31962.471967.901954.831. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory CopyingLinux 5.4Linux 5.9.1Linux 5.10 Git30060090012001500Min: 1943.34 / Avg: 1962.47 / Max: 1980.37Min: 1959.59 / Avg: 1967.9 / Max: 1980.76Min: 1928.87 / Avg: 1954.83 / Max: 1985.911. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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: 19Linux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 315.315.415.41. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19Linux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 15.3 / Avg: 15.33 / Max: 15.4Min: 15.4 / Avg: 15.4 / Max: 15.4Min: 15.4 / Avg: 15.4 / Max: 15.41. (CC) gcc options: -O3 -pthread -lz -llzma

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyLinux 5.4Linux 5.9.1Linux 5.10 Git4080120160200159158159

Timed Apache Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 342.6042.8442.87
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git918273645Min: 42.54 / Avg: 42.6 / Max: 42.66Min: 42.75 / Avg: 42.84 / Max: 42.96Min: 42.8 / Avg: 42.87 / Max: 43.01

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: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git0.360.721.081.441.8SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.601.591.601. (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: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 1.6 / Avg: 1.6 / Max: 1.61Min: 1.59 / Avg: 1.59 / Max: 1.6Min: 1.59 / Avg: 1.6 / Max: 1.61. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 SceneLinux 5.4Linux 5.9.1Linux 5.10 Git100200300400500SE +/- 1.62, N = 3SE +/- 1.20, N = 3SE +/- 1.21, N = 3481.61481.82478.881. (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 SceneLinux 5.4Linux 5.9.1Linux 5.10 Git90180270360450Min: 478.63 / Avg: 481.61 / Max: 484.19Min: 479.66 / Avg: 481.82 / Max: 483.82Min: 477.31 / Avg: 478.88 / Max: 481.251. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -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 20200916Target: CPU - Model: resnet50Linux 5.4Linux 5.9.1Linux 5.10 Git1428425670SE +/- 0.38, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 362.6262.2462.37MIN: 60.93 / MAX: 99.21MIN: 61.41 / MAX: 88.16MIN: 61.54 / MAX: 65.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50Linux 5.4Linux 5.9.1Linux 5.10 Git1224364860Min: 61.87 / Avg: 62.62 / Max: 63.03Min: 62 / Avg: 62.24 / Max: 62.44Min: 62.1 / Avg: 62.37 / Max: 62.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git400800120016002000SE +/- 8.56, N = 3SE +/- 8.86, N = 3SE +/- 7.28, N = 31733.371737.831727.62
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git30060090012001500Min: 1721.07 / Avg: 1733.37 / Max: 1749.83Min: 1726.07 / Avg: 1737.83 / Max: 1755.18Min: 1717.54 / Avg: 1727.62 / Max: 1741.76

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, LosslessLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 324.4724.4524.591. (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, LosslessLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.29 / Avg: 24.47 / Max: 24.56Min: 24.32 / Avg: 24.45 / Max: 24.62Min: 24.39 / Avg: 24.59 / Max: 24.711. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 4KLinux 5.4Linux 5.9.1Linux 5.10 Git1.1612.3223.4834.6445.805SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.135.165.141. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 5.13 / Avg: 5.13 / Max: 5.14Min: 5.15 / Avg: 5.16 / Max: 5.17Min: 5.13 / Avg: 5.14 / Max: 5.151. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 0Linux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 311.7511.7111.771. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 0Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 11.68 / Avg: 11.75 / Max: 11.79Min: 11.67 / Avg: 11.71 / Max: 11.75Min: 11.74 / Avg: 11.77 / Max: 11.821. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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 DynamicsLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 320.5820.4720.53
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 20.51 / Avg: 20.58 / Max: 20.62Min: 20.43 / Avg: 20.47 / Max: 20.52Min: 20.39 / Avg: 20.53 / Max: 20.65

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 2020-06-28Linux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 321.8721.8121.751. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28Linux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 21.73 / Avg: 21.87 / Max: 22.1Min: 21.62 / Avg: 21.81 / Max: 22.03Min: 21.62 / Avg: 21.75 / Max: 22.011. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

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: DefaultLinux 5.4Linux 5.9.1Linux 5.10 Git0.4010.8021.2031.6042.005SE +/- 0.006, N = 3SE +/- 0.007, N = 3SE +/- 0.005, N = 31.7811.7821.7731. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 1.77 / Avg: 1.78 / Max: 1.79Min: 1.77 / Avg: 1.78 / Max: 1.8Min: 1.77 / Avg: 1.77 / Max: 1.781. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: Glibc Qsort Data SortingLinux 5.4Linux 5.9.1Linux 5.10 Git1020304050SE +/- 0.32, N = 3SE +/- 0.50, N = 3SE +/- 0.46, N = 343.1443.0243.231. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data SortingLinux 5.4Linux 5.9.1Linux 5.10 Git918273645Min: 42.57 / Avg: 43.14 / Max: 43.67Min: 42.2 / Avg: 43.02 / Max: 43.93Min: 42.6 / Avg: 43.23 / Max: 44.131. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileLinux 5.4Linux 5.9.1Linux 5.10 Git50100150200250210210209

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonLinux 5.4Linux 5.9.1Linux 5.10 Git140280420560700SE +/- 1.76, N = 3SE +/- 2.33, N = 3SE +/- 1.45, N = 3634637636
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonLinux 5.4Linux 5.9.1Linux 5.10 Git110220330440550Min: 631 / Avg: 633.67 / Max: 637Min: 632 / Avg: 636.67 / Max: 639Min: 633 / Avg: 635.67 / Max: 638

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git612182430SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 324.8224.8124.711. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 24.66 / Avg: 24.82 / Max: 25.1Min: 24.7 / Avg: 24.81 / Max: 24.91Min: 24.68 / Avg: 24.71 / Max: 24.771. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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 FloatLinux 5.4Linux 5.9.1Linux 5.10 Git60K120K180K240K300KSE +/- 199.88, N = 3SE +/- 73.99, N = 3SE +/- 31.47, N = 3283570282323282261
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatLinux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KMin: 283206 / Avg: 283570.33 / Max: 283895Min: 282203 / Avg: 282323 / Max: 282458Min: 282215 / Avg: 282260.67 / Max: 282321

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Linux 5.4Linux 5.9.1Linux 5.10 Git90180270360450SE +/- 0.33, N = 3SE +/- 0.33, N = 3435436434
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Linux 5.4Linux 5.9.1Linux 5.10 Git80160240320400Min: 436 / Avg: 436.33 / Max: 437Min: 433 / Avg: 433.67 / Max: 434

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: 8Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.014, N = 3SE +/- 0.009, N = 3SE +/- 0.015, N = 38.7078.7318.7471. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 8.69 / Avg: 8.71 / Max: 8.74Min: 8.72 / Avg: 8.73 / Max: 8.75Min: 8.72 / Avg: 8.75 / Max: 8.771. (CXX) g++ options: -O3 -fPIC

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 322.7322.6322.70
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 22.61 / Avg: 22.73 / Max: 22.83Min: 22.61 / Avg: 22.63 / Max: 22.67Min: 22.64 / Avg: 22.7 / Max: 22.8

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100Linux 5.4Linux 5.9.1Linux 5.10 Git30K60K90K120K150KSE +/- 374.28, N = 3SE +/- 305.63, N = 3SE +/- 28.30, N = 31166591171581166481. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100Linux 5.4Linux 5.9.1Linux 5.10 Git20K40K60K80K100KMin: 116148 / Avg: 116658.67 / Max: 117388Min: 116837 / Avg: 117158 / Max: 117769Min: 116600 / Avg: 116648.33 / Max: 1166981. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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: SqueezeNetLinux 5.4Linux 5.9.1Linux 5.10 Git90K180K270K360K450KSE +/- 109.37, N = 3SE +/- 56.63, N = 3SE +/- 119.79, N = 3419509417749417931
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetLinux 5.4Linux 5.9.1Linux 5.10 Git70K140K210K280K350KMin: 419357 / Avg: 419508.67 / Max: 419721Min: 417683 / Avg: 417749.33 / Max: 417862Min: 417739 / Avg: 417930.67 / Max: 418151

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: ThoroughLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 383.8683.5483.511. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughLinux 5.4Linux 5.9.1Linux 5.10 Git1632486480Min: 83.69 / Avg: 83.86 / Max: 84.18Min: 83.5 / Avg: 83.54 / Max: 83.58Min: 83.45 / Avg: 83.51 / Max: 83.581. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 322.0022.0822.091. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 21.84 / Avg: 22 / Max: 22.09Min: 21.97 / Avg: 22.08 / Max: 22.24Min: 21.87 / Avg: 22.09 / Max: 22.271. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 V2Linux 5.4Linux 5.9.1Linux 5.10 Git1.2M2.4M3.6M4.8M6MSE +/- 548.09, N = 3SE +/- 578.92, N = 3SE +/- 503.47, N = 3543215054101675411013
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Linux 5.4Linux 5.9.1Linux 5.10 Git900K1800K2700K3600K4500KMin: 5431330 / Avg: 5432150 / Max: 5433190Min: 5409010 / Avg: 5410166.67 / Max: 5410790Min: 5410490 / Avg: 5411013.33 / Max: 5412020

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: 2Linux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.52, N = 3134.64134.32134.101. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2Linux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 134.53 / Avg: 134.64 / Max: 134.75Min: 133.94 / Avg: 134.32 / Max: 134.53Min: 133.29 / Avg: 134.1 / Max: 135.081. (CXX) g++ options: -O3 -fPIC

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200Linux 5.4Linux 5.9.1Linux 5.10 Git20K40K60K80K100KSE +/- 172.40, N = 3SE +/- 52.00, N = 3SE +/- 52.66, N = 39409893721937231. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200Linux 5.4Linux 5.9.1Linux 5.10 Git16K32K48K64K80KMin: 93759 / Avg: 94098 / Max: 94322Min: 93618 / Avg: 93721 / Max: 93785Min: 93658 / Avg: 93722.67 / Max: 938271. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 V4Linux 5.4Linux 5.9.1Linux 5.10 Git1.3M2.6M3.9M5.2M6.5MSE +/- 573.65, N = 3SE +/- 180.83, N = 3SE +/- 200.00, N = 3598758359643105964510
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Linux 5.4Linux 5.9.1Linux 5.10 Git1000K2000K3000K4000K5000KMin: 5986470 / Avg: 5987583.33 / Max: 5988380Min: 5963950 / Avg: 5964310 / Max: 5964520Min: 5964310 / Avg: 5964510 / Max: 5964910

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: 3Linux 5.4Linux 5.9.1Linux 5.10 Git6001200180024003000SE +/- 6.14, N = 3SE +/- 6.96, N = 3SE +/- 6.19, N = 32751.32753.02761.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3Linux 5.4Linux 5.9.1Linux 5.10 Git5001000150020002500Min: 2739.5 / Avg: 2751.27 / Max: 2760.2Min: 2741.7 / Avg: 2753 / Max: 2765.7Min: 2749.1 / Avg: 2761.47 / Max: 2768.11. (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 20200916Target: CPU-v3-v3 - Model: mobilenet-v3Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.428.398.40MIN: 8.2 / MAX: 25.36MIN: 8.32 / MAX: 9.97MIN: 8.31 / MAX: 10.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 8.33 / Avg: 8.42 / Max: 8.5Min: 8.38 / Avg: 8.39 / Max: 8.4Min: 8.38 / Avg: 8.4 / Max: 8.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18Linux 5.4Linux 5.9.1Linux 5.10 Git714212835SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 328.0927.9928.05MIN: 27.69 / MAX: 51.11MIN: 27.7 / MAX: 46.07MIN: 27.79 / MAX: 61.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18Linux 5.4Linux 5.9.1Linux 5.10 Git612182430Min: 28.03 / Avg: 28.09 / Max: 28.17Min: 27.82 / Avg: 27.99 / Max: 28.11Min: 27.99 / Avg: 28.05 / Max: 28.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0Linux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 314.0614.1014.11MIN: 13.81 / MAX: 26.67MIN: 14.01 / MAX: 15.64MIN: 14 / MAX: 14.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0Linux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 13.95 / Avg: 14.06 / Max: 14.13Min: 14.09 / Avg: 14.1 / Max: 14.11Min: 14.08 / Avg: 14.11 / Max: 14.151. (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: 10Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.004, N = 3SE +/- 0.009, N = 3SE +/- 0.013, N = 37.9807.9527.9761. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 7.97 / Avg: 7.98 / Max: 7.99Min: 7.93 / Avg: 7.95 / Max: 7.96Min: 7.96 / Avg: 7.98 / Max: 81. (CXX) g++ options: -O3 -fPIC

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: MallocLinux 5.4Linux 5.9.1Linux 5.10 Git3M6M9M12M15MSE +/- 12161.58, N = 3SE +/- 1402.16, N = 3SE +/- 15546.64, N = 315780304.3615798673.9315835328.301. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocLinux 5.4Linux 5.9.1Linux 5.10 Git3M6M9M12M15MMin: 15756062.55 / Avg: 15780304.36 / Max: 15794146.57Min: 15796504.09 / Avg: 15798673.93 / Max: 15801297.35Min: 15818477.01 / Avg: 15835328.3 / Max: 158663841. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 CompileLinux 5.4Linux 5.9.1Linux 5.10 Git50100150200250SE +/- 0.27, N = 3SE +/- 0.14, N = 3SE +/- 0.29, N = 3209.17208.48209.00
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileLinux 5.4Linux 5.9.1Linux 5.10 Git4080120160200Min: 208.75 / Avg: 209.17 / Max: 209.68Min: 208.24 / Avg: 208.48 / Max: 208.72Min: 208.52 / Avg: 209 / Max: 209.53

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 BenchmarkLinux 5.4Linux 5.9.1Linux 5.10 Git510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 321.3721.4321.441. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkLinux 5.4Linux 5.9.1Linux 5.10 Git510152025Min: 21.34 / Avg: 21.37 / Max: 21.41Min: 21.4 / Avg: 21.43 / Max: 21.45Min: 21.43 / Avg: 21.44 / Max: 21.471. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -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 20200916Target: CPU-v2-v2 - Model: mobilenet-v2Linux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 39.289.289.25MIN: 9.05 / MAX: 22.88MIN: 9.17 / MAX: 20.47MIN: 9.18 / MAX: 10.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 9.24 / Avg: 9.28 / Max: 9.34Min: 9.25 / Avg: 9.28 / Max: 9.32Min: 9.25 / Avg: 9.25 / Max: 9.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 36.386.376.39
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 6.37 / Avg: 6.38 / Max: 6.4Min: 6.35 / Avg: 6.37 / Max: 6.39Min: 6.36 / Avg: 6.39 / Max: 6.42

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 MobileLinux 5.4Linux 5.9.1Linux 5.10 Git70K140K210K280K350KSE +/- 47.06, N = 3SE +/- 73.96, N = 3SE +/- 49.60, N = 3304512303560303578
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileLinux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KMin: 304441 / Avg: 304512 / Max: 304601Min: 303421 / Avg: 303560.33 / Max: 303673Min: 303488 / Avg: 303578.33 / Max: 303659

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsLinux 5.4Linux 5.9.1Linux 5.10 Git816243240SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 332.332.332.2
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsLinux 5.4Linux 5.9.1Linux 5.10 Git714212835Min: 32.2 / Avg: 32.27 / Max: 32.3Min: 32.2 / Avg: 32.27 / Max: 32.4Min: 32.1 / Avg: 32.23 / Max: 32.4

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git14002800420056007000SE +/- 8.15, N = 3SE +/- 5.30, N = 3SE +/- 0.41, N = 36320.556320.396301.44
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git11002200330044005500Min: 6304.53 / Avg: 6320.55 / Max: 6331.17Min: 6311.64 / Avg: 6320.39 / Max: 6329.94Min: 6300.78 / Avg: 6301.44 / Max: 6302.19

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 RNALinux 5.4Linux 5.9.1Linux 5.10 Git48121620SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 313.6513.6913.661. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNALinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 13.53 / Avg: 13.65 / Max: 13.78Min: 13.58 / Avg: 13.69 / Max: 13.87Min: 13.59 / Avg: 13.66 / Max: 13.751. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150SE +/- 0.97, N = 3SE +/- 0.49, N = 3SE +/- 1.21, N = 3113.67113.98114.011. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 111.85 / Avg: 113.67 / Max: 115.17Min: 113.47 / Avg: 113.98 / Max: 114.96Min: 111.85 / Avg: 114 / Max: 116.051. (CXX) g++ options: -O2 -lOpenCL

Sunflow Rendering System

This test runs benchmarks of the Sunflow Rendering System. The Sunflow Rendering System is an open-source render engine for photo-realistic image synthesis with a ray-tracing core. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image SynthesisLinux 5.4Linux 5.9.1Linux 5.10 Git0.7741.5482.3223.0963.87SE +/- 0.050, N = 4SE +/- 0.048, N = 15SE +/- 0.032, N = 153.4393.4303.440MIN: 3.02 / MAX: 4.18MIN: 3.02 / MAX: 4.29MIN: 2.93 / MAX: 4.32
OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image SynthesisLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 3.3 / Avg: 3.44 / Max: 3.53Min: 3.23 / Avg: 3.43 / Max: 3.95Min: 3.26 / Avg: 3.44 / Max: 3.68

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 0.7.0Video Input: Chimera 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git4080120160200SE +/- 0.20, N = 3SE +/- 0.29, N = 3SE +/- 0.51, N = 3181.78182.27181.94MIN: 137.37 / MAX: 309.56MIN: 136.66 / MAX: 307.75MIN: 135.93 / MAX: 3121. (CC) gcc options: -pthread -ldl -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 181.45 / Avg: 181.78 / Max: 182.14Min: 181.94 / Avg: 182.27 / Max: 182.84Min: 181.29 / Avg: 181.94 / Max: 182.951. (CC) gcc options: -pthread -ldl -lm

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: AtomicLinux 5.4Linux 5.9.1Linux 5.10 Git70K140K210K280K350KSE +/- 156.05, N = 3SE +/- 46.97, N = 3SE +/- 54.89, N = 3304850.38304317.83304118.871. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicLinux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KMin: 304544.74 / Avg: 304850.38 / Max: 305057.89Min: 304244.64 / Avg: 304317.83 / Max: 304405.42Min: 304010.37 / Avg: 304118.87 / Max: 304187.641. (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 StressLinux 5.4Linux 5.9.1Linux 5.10 Git30060090012001500SE +/- 0.58, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 31214.241216.721216.911. (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 StressLinux 5.4Linux 5.9.1Linux 5.10 Git2004006008001000Min: 1213.15 / Avg: 1214.24 / Max: 1215.11Min: 1216.47 / Avg: 1216.72 / Max: 1216.9Min: 1216.89 / Avg: 1216.91 / Max: 1216.921. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 20200916Target: CPU - Model: mnasnetLinux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 39.389.369.37MIN: 9.23 / MAX: 10.34MIN: 9.29 / MAX: 10.4MIN: 9.3 / MAX: 10.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 9.32 / Avg: 9.38 / Max: 9.44Min: 9.34 / Avg: 9.36 / Max: 9.39Min: 9.36 / Avg: 9.37 / Max: 9.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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, Highest CompressionLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.033, N = 3SE +/- 0.024, N = 3SE +/- 0.051, N = 38.4668.4568.4731. (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, Highest CompressionLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 8.43 / Avg: 8.47 / Max: 8.53Min: 8.43 / Avg: 8.46 / Max: 8.5Min: 8.42 / Avg: 8.47 / Max: 8.571. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KSE +/- 12.68, N = 3SE +/- 13.78, N = 3SE +/- 11.08, N = 39779.729760.439764.85
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KMin: 9766.7 / Avg: 9779.72 / Max: 9805.07Min: 9746.61 / Avg: 9760.43 / Max: 9787.99Min: 9742.72 / Avg: 9764.85 / Max: 9776.99

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 9.6.0+dfsgProcessing 60 Page PDF DocumentLinux 5.4Linux 5.9.1Linux 5.10 Git1530456075SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 366.1766.3066.28
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 9.6.0+dfsgProcessing 60 Page PDF DocumentLinux 5.4Linux 5.9.1Linux 5.10 Git1326395265Min: 65.9 / Avg: 66.17 / Max: 66.4Min: 66.08 / Avg: 66.3 / Max: 66.54Min: 66.04 / Avg: 66.28 / Max: 66.45

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git14002800420056007000SE +/- 7.90, N = 3SE +/- 4.12, N = 3SE +/- 1.64, N = 36312.556305.726301.06
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git11002200330044005500Min: 6296.85 / Avg: 6312.55 / Max: 6322.03Min: 6300.75 / Avg: 6305.72 / Max: 6313.9Min: 6298.05 / Avg: 6301.06 / Max: 6303.7

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 MathLinux 5.4Linux 5.9.1Linux 5.10 Git5K10K15K20K25KSE +/- 5.59, N = 3SE +/- 3.99, N = 3SE +/- 8.45, N = 322346.7622371.5622385.341. (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 MathLinux 5.4Linux 5.9.1Linux 5.10 Git4K8K12K16K20KMin: 22338.29 / Avg: 22346.76 / Max: 22357.31Min: 22365.68 / Avg: 22371.56 / Max: 22379.16Min: 22375.19 / Avg: 22385.34 / Max: 22402.111. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100Linux 5.4Linux 5.9.1Linux 5.10 Git10K20K30K40K50KSE +/- 83.48, N = 3SE +/- 27.73, N = 3SE +/- 28.42, N = 34686646918469411. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100Linux 5.4Linux 5.9.1Linux 5.10 Git8K16K24K32K40KMin: 46719 / Avg: 46866.33 / Max: 47008Min: 46869 / Avg: 46918 / Max: 46965Min: 46897 / Avg: 46940.67 / Max: 469941. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceLinux 5.4Linux 5.9.1Linux 5.10 Git140280420560700SE +/- 0.67, N = 3SE +/- 0.88, N = 3639639638
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceLinux 5.4Linux 5.9.1Linux 5.10 Git110220330440550Min: 638 / Avg: 639.33 / Max: 640Min: 637 / Avg: 638.33 / Max: 640

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: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 313.2113.2013.191. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumLinux 5.4Linux 5.9.1Linux 5.10 Git48121620Min: 13.2 / Avg: 13.21 / Max: 13.22Min: 13.13 / Avg: 13.2 / Max: 13.31Min: 13.13 / Avg: 13.19 / Max: 13.31. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -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 2020-09-17Model: mobilenet-v1-1.0Linux 5.4Linux 5.9.1Linux 5.10 Git3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.2010.1810.19MIN: 10.05 / MAX: 22.26MIN: 10.12 / MAX: 23.11MIN: 10.13 / MAX: 22.161. (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 2020-09-17Model: mobilenet-v1-1.0Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 10.16 / Avg: 10.2 / Max: 10.22Min: 10.16 / Avg: 10.18 / Max: 10.2Min: 10.17 / Avg: 10.19 / Max: 10.211. (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

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3110.02109.88109.951. RawTherapee, version 5.8, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 109.92 / Avg: 110.02 / Max: 110.17Min: 109.78 / Avg: 109.88 / Max: 109.95Min: 109.8 / Avg: 109.95 / Max: 110.141. RawTherapee, version 5.8, command line.

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: ExhaustiveLinux 5.4Linux 5.9.1Linux 5.10 Git150300450600750SE +/- 0.32, N = 3SE +/- 1.51, N = 3SE +/- 0.46, N = 3678.88678.55677.991. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveLinux 5.4Linux 5.9.1Linux 5.10 Git120240360480600Min: 678.29 / Avg: 678.88 / Max: 679.39Min: 676.82 / Avg: 678.55 / Max: 681.56Min: 677.32 / Avg: 677.99 / Max: 678.871. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -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: Matrix MathLinux 5.4Linux 5.9.1Linux 5.10 Git3K6K9K12K15KSE +/- 27.13, N = 3SE +/- 31.67, N = 3SE +/- 36.38, N = 316244.7716243.9916265.101. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix MathLinux 5.4Linux 5.9.1Linux 5.10 Git3K6K9K12K15KMin: 16209.24 / Avg: 16244.77 / Max: 16298.04Min: 16210.71 / Avg: 16243.99 / Max: 16307.3Min: 16204.97 / Avg: 16265.1 / Max: 16330.631. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2Linux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 384.2984.3684.271. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2Linux 5.4Linux 5.9.1Linux 5.10 Git1632486480Min: 84.28 / Avg: 84.29 / Max: 84.31Min: 84.33 / Avg: 84.36 / Max: 84.43Min: 84.21 / Avg: 84.27 / Max: 84.331. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteLinux 5.4Linux 5.9.1Linux 5.10 Git60120180240300SE +/- 0.67, N = 3SE +/- 0.29, N = 3SE +/- 0.28, N = 3293.28292.97293.041. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteLinux 5.4Linux 5.9.1Linux 5.10 Git50100150200250Min: 292.55 / Avg: 293.28 / Max: 294.63Min: 292.62 / Avg: 292.97 / Max: 293.54Min: 292.54 / Avg: 293.04 / Max: 293.51. (CXX) g++ options: -O2 -lOpenCL

GNU Octave Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 5.2.0Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.041, N = 5SE +/- 0.052, N = 5SE +/- 0.048, N = 58.3428.3488.350
OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 5.2.0Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 8.29 / Avg: 8.34 / Max: 8.51Min: 8.26 / Avg: 8.35 / Max: 8.55Min: 8.25 / Avg: 8.35 / Max: 8.53

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KSE +/- 4.65, N = 3SE +/- 0.66, N = 3SE +/- 4.22, N = 39784.949777.689786.97
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git2K4K6K8K10KMin: 9778.84 / Avg: 9784.94 / Max: 9794.07Min: 9776.59 / Avg: 9777.68 / Max: 9778.87Min: 9780.44 / Avg: 9786.97 / Max: 9794.86

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200Linux 5.4Linux 5.9.1Linux 5.10 Git50K100K150K200K250KSE +/- 785.08, N = 3SE +/- 584.28, N = 3SE +/- 182.54, N = 32330772328752329271. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200Linux 5.4Linux 5.9.1Linux 5.10 Git40K80K120K160K200KMin: 232217 / Avg: 233077.33 / Max: 234645Min: 231746 / Avg: 232875.33 / Max: 233700Min: 232569 / Avg: 232927.33 / Max: 2331671. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDLinux 5.4Linux 5.9.1Linux 5.10 Git130260390520650SE +/- 1.33, N = 3SE +/- 1.90, N = 3SE +/- 2.70, N = 3619.24619.54619.721. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDLinux 5.4Linux 5.9.1Linux 5.10 Git110220330440550Min: 616.68 / Avg: 619.24 / Max: 621.15Min: 616.89 / Avg: 619.54 / Max: 623.23Min: 617.01 / Avg: 619.72 / Max: 625.121. (CXX) g++ options: -O2 -lOpenCL

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 393.0293.0693.031. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 TimesLinux 5.4Linux 5.9.1Linux 5.10 Git20406080100Min: 92.66 / Avg: 93.02 / Max: 93.3Min: 92.81 / Avg: 93.06 / Max: 93.34Min: 92.84 / Avg: 93.03 / Max: 93.151. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goLinux 5.4Linux 5.9.1Linux 5.10 Git70140210280350SE +/- 0.58, N = 3SE +/- 0.58, N = 3319319319
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goLinux 5.4Linux 5.9.1Linux 5.10 Git60120180240300Min: 318 / Avg: 319 / Max: 320Min: 318 / Avg: 319 / Max: 320

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.09230.18460.27690.36920.4615SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.410.410.41
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.41 / Avg: 0.41 / Max: 0.41Min: 0.41 / Avg: 0.41 / Max: 0.41Min: 0.41 / Avg: 0.41 / Max: 0.41

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.09230.18460.27690.36920.4615SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.410.410.41
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.41 / Avg: 0.41 / Max: 0.41Min: 0.41 / Avg: 0.41 / Max: 0.41Min: 0.41 / Avg: 0.41 / Max: 0.41

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.14180.28360.42540.56720.709SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.630.630.63
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 0.63 / Avg: 0.63 / Max: 0.63Min: 0.63 / Avg: 0.63 / Max: 0.63Min: 0.63 / Avg: 0.63 / Max: 0.63

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git0.14180.28360.42540.56720.709SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.630.630.63
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 0.63 / Avg: 0.63 / Max: 0.63Min: 0.63 / Avg: 0.63 / Max: 0.63Min: 0.63 / Avg: 0.63 / Max: 0.63

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 20200916Target: CPU - Model: blazefaceLinux 5.4Linux 5.9.1Linux 5.10 Git0.48380.96761.45141.93522.419SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.152.152.15MIN: 2.08 / MAX: 3.05MIN: 2.11 / MAX: 4.63MIN: 2.11 / MAX: 4.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.14 / Avg: 2.15 / Max: 2.16Min: 2.14 / Avg: 2.15 / Max: 2.17Min: 2.14 / Avg: 2.15 / Max: 2.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2Linux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 36.666.666.66MIN: 6.45 / MAX: 16.83MIN: 6.61 / MAX: 6.9MIN: 6.6 / MAX: 7.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2Linux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 6.64 / Avg: 6.66 / Max: 6.67Min: 6.65 / Avg: 6.66 / Max: 6.68Min: 6.65 / Avg: 6.66 / Max: 6.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.4Linux 5.9.1Linux 5.10 Git0.0450.090.1350.180.225SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.20.20.21. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.2 / Avg: 0.2 / Max: 0.21. (CXX) g++ options: -O3 -lsnappy -lpthread

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 0 - Input: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git0.0110.0220.0330.0440.055SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0490.0490.0491. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pLinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.051. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git0.52881.05761.58642.11522.644SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.352.352.351. (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 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git246810Min: 2.34 / Avg: 2.35 / Max: 2.36Min: 2.33 / Avg: 2.35 / Max: 2.36Min: 2.35 / Avg: 2.35 / Max: 2.351. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git0.0360.0720.1080.1440.18SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 150.160.160.161. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-PassLinux 5.4Linux 5.9.1Linux 5.10 Git12345Min: 0.16 / Avg: 0.16 / Max: 0.17Min: 0.16 / Avg: 0.16 / Max: 0.17Min: 0.16 / Avg: 0.16 / Max: 0.171. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Monte Carlo Simulations of Ionised Nebulae

Mocassin is the Monte Carlo Simulations of Ionised Nebulae. MOCASSIN is a fully 3D or 2D photoionisation and dust radiative transfer code which employs a Monte Carlo approach to the transfer of radiation through media of arbitrary geometry and density distribution. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.0Linux 5.4Linux 5.9.1Linux 5.10 Git70140210280350SE +/- 1.00, N = 33173173171. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.0Linux 5.4Linux 5.9.1Linux 5.10 Git60120180240300Min: 316 / Avg: 317 / Max: 3191. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.10 Git9K18K27K36K45KSE +/- 8014.44, N = 8SE +/- 13950.12, N = 919159.941400.2
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.4Linux 5.10 Git7K14K21K28K35KMin: 3255.1 / Avg: 19159.86 / Max: 73061.4Min: 882.5 / Avg: 41400.22 / Max: 117929.3

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: System V Message PassingLinux 5.4Linux 5.9.1Linux 5.10 Git900K1800K2700K3600K4500KSE +/- 236092.88, N = 12SE +/- 44477.87, N = 15SE +/- 97114.56, N = 153194317.083431597.324269857.661. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingLinux 5.4Linux 5.9.1Linux 5.10 Git700K1400K2100K2800K3500KMin: 2248723.33 / Avg: 3194317.08 / Max: 5497872.65Min: 3099321.5 / Avg: 3431597.32 / Max: 3663714.93Min: 3565692.73 / Avg: 4269857.66 / Max: 4905260.331. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.23, N = 15SE +/- 0.17, N = 15SE +/- 0.13, N = 155.796.456.621. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 4.7 / Avg: 5.79 / Max: 8.2Min: 4.93 / Avg: 6.45 / Max: 7.73Min: 5.83 / Avg: 6.62 / Max: 7.81. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3Linux 5.4Linux 5.9.1Linux 5.10 Git4080120160200SE +/- 4.66, N = 12SE +/- 0.05, N = 3SE +/- 0.08, N = 3180.01172.39172.361. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3Linux 5.4Linux 5.9.1Linux 5.10 Git306090120150Min: 172.26 / Avg: 180.01 / Max: 224.51Min: 172.29 / Avg: 172.39 / Max: 172.44Min: 172.23 / Avg: 172.36 / Max: 172.521. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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: FastLinux 5.4Linux 5.9.1Linux 5.10 Git246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 155.605.588.211. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: FastLinux 5.4Linux 5.9.1Linux 5.10 Git3691215Min: 5.59 / Avg: 5.6 / Max: 5.6Min: 5.57 / Avg: 5.58 / Max: 5.58Min: 5.55 / Avg: 8.21 / Max: 9.981. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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: EigenLinux 5.4Linux 5.9.1Linux 5.10 Git100200300400500SE +/- 4.91, N = 3SE +/- 5.72, N = 9SE +/- 6.34, N = 94412932831. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenLinux 5.4Linux 5.9.1Linux 5.10 Git80160240320400Min: 431 / Avg: 440.67 / Max: 447Min: 260 / Avg: 293.11 / Max: 318Min: 261 / Avg: 283.22 / Max: 3171. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASLinux 5.4Linux 5.9.1Linux 5.10 Git90180270360450SE +/- 4.33, N = 3SE +/- 7.71, N = 94322892791. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASLinux 5.4Linux 5.9.1Linux 5.10 Git80160240320400Min: 428 / Avg: 432.33 / Max: 441Min: 255 / Avg: 289 / Max: 3201. (CXX) g++ options: -flto -pthread

197 Results Shown

PyPerformance
Stress-NG:
  NUMA
  Context Switching
  Forking
  Semaphores
LevelDB:
  Overwrite:
    MB/s
    Microseconds Per Op
  Rand Fill:
    Microseconds Per Op
    MB/s
oneDNN
Stress-NG
LevelDB
Stress-NG
LevelDB:
  Seq Fill
  Hot Read
  Seq Fill
oneDNN
LevelDB:
  Fill Sync
  Seek Rand
InfluxDB
Stress-NG
LevelDB
NCNN
KeyDB
Apache CouchDB
dav1d
Stress-NG
Timed HMMer Search
oneDNN:
  IP Batch 1D - f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
FFTE
oneDNN
G'MIC
SVT-AV1
InfluxDB
DaCapo Benchmark
NCNN:
  CPU - yolov4-tiny
  CPU - mobilenet
GLmark2
DaCapo Benchmark
OpenVINO
Kvazaar
Mlpack Benchmark
TNN
LuxCoreRender
BRL-CAD
DaCapo Benchmark
NeatBench
Mobile Neural Network
7-Zip Compression
LuxCoreRender
SVT-VP9
OpenVINO
WebP Image Encode
Basis Universal
Rodinia
eSpeak-NG Speech Engine
PyPerformance
SVT-VP9
Kvazaar
AOM AV1
librsvg
OpenVINO
PyPerformance
Mobile Neural Network
oneDNN
dav1d
Stress-NG:
  Crypto
  Glibc C String Functions
Tesseract OCR
oneDNN
Kvazaar
Hierarchical INTegration
GROMACS
BYTE Unix Benchmark
WebP Image Encode
Kvazaar
NAMD
Incompact3D
DaCapo Benchmark
AOM AV1
Build2
Montage Astronomical Image Mosaic Engine
NCNN
PyPerformance
Basis Universal
Rodinia
dav1d
C-Blosc
Hugin
SVT-VP9
LibreOffice
Kvazaar
Timed Linux Kernel Compilation
TensorFlow Lite
Mobile Neural Network:
  resnet-v2-50
  inception-v3
libavif avifenc
PyPerformance
NCNN
oneDNN
LAMMPS Molecular Dynamics Simulator
NCNN
TNN
Chaos Group V-RAY
Mlpack Benchmark
AOM AV1
SVT-AV1
PyPerformance
Stress-NG
Zstd Compression
PyPerformance
Timed Apache Compilation
Kvazaar
YafaRay
NCNN
OpenVINO
WebP Image Encode
x265
Basis Universal
Dolfyn
RNNoise
WebP Image Encode
Stress-NG
PyPerformance:
  regex_compile
  pickle_pure_python
G'MIC
TensorFlow Lite
PyPerformance
libavif avifenc
Mlpack Benchmark
Caffe
TensorFlow Lite
ASTC Encoder
x265
TensorFlow Lite
libavif avifenc
Caffe
TensorFlow Lite
Zstd Compression
NCNN:
  CPU-v3-v3 - mobilenet-v3
  CPU - resnet18
  CPU - efficientnet-b0
libavif avifenc
Stress-NG
Timed GDB GNU Debugger Compilation
LibRaw
NCNN
Mlpack Benchmark
TensorFlow Lite
PyPerformance
OpenVINO
Timed MAFFT Alignment
Rodinia
Sunflow Rendering System
dav1d
Stress-NG:
  Atomic
  CPU Stress
NCNN
WebP Image Encode
OpenVINO
OCRMyPDF
OpenVINO
Stress-NG
Caffe
PyPerformance
ASTC Encoder
Mobile Neural Network
RawTherapee
ASTC Encoder
Stress-NG
Basis Universal
Rodinia
GNU Octave Benchmark
OpenVINO
Caffe
Rodinia
G'MIC
PyPerformance
OpenVINO:
  Person Detection 0106 FP32 - CPU
  Person Detection 0106 FP16 - CPU
  Face Detection 0106 FP32 - CPU
  Face Detection 0106 FP16 - CPU
NCNN:
  CPU - blazeface
  CPU - shufflenet-v2
LevelDB
SVT-AV1
AOM AV1:
  Speed 6 Two-Pass
  Speed 0 Two-Pass
Monte Carlo Simulations of Ionised Nebulae
InfluxDB
Stress-NG:
  System V Message Passing
  MMAP
Basis Universal
ASTC Encoder
LeelaChessZero:
  Eigen
  BLAS

Linux 5.4

Processor: AMD Ryzen 3 1300X @ 3.50GHz (4 Cores), Motherboard: ASRock AB350 Pro4 (P3.20 BIOS), Chipset: AMD 17h, Memory: 8GB, Disk: 128GB ADATA SU800, Graphics: Sapphire AMD Radeon R7 260X/360 2GB, Audio: AMD Tobago HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.4.0-51-generic (x86_64), Desktop: GNOME Shell 3.36.3, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 ondemand - CPU Microcode: 0x8001129
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 19 October 2020 20:15 by user phoronix.

Linux 5.9.1

Processor: AMD Ryzen 3 1300X @ 3.50GHz (4 Cores), Motherboard: ASRock AB350 Pro4 (P3.20 BIOS), Chipset: AMD 17h, Memory: 8GB, Disk: 128GB ADATA SU800, Graphics: Sapphire AMD Radeon R7 260X/360 2GB, Audio: AMD Tobago HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.9.1-050901-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.5 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 ondemand - CPU Microcode: 0x8001129
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 October 2020 14:17 by user phoronix.

Linux 5.10 Git

Processor: AMD Ryzen 3 1300X @ 3.50GHz (4 Cores), Motherboard: ASRock AB350 Pro4 (P3.20 BIOS), Chipset: AMD 17h, Memory: 8GB, Disk: 128GB ADATA SU800, Graphics: Sapphire AMD Radeon R7 260X/360 2GB, Audio: AMD Tobago HDMI Audio, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.9.0-050900daily20201021-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.5 Mesa 20.0.8 (LLVM 10.0.0), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 ondemand - CPU Microcode: 0x8001129
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 October 2020 08:49 by user phoronix.