Core i5 6500 Xmas

Intel Core i5-6500 testing with a Gigabyte Z170M-D3H-CF (F22f BIOS) and Gigabyte Intel HD 530 3GB 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 2012230-HA-COREI565062
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:

Audio Encoding 3 Tests
Bioinformatics 2 Tests
Chess Test Suite 3 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 9 Tests
CPU Massive 11 Tests
Creator Workloads 10 Tests
Database Test Suite 2 Tests
Encoding 4 Tests
Game Development 2 Tests
HPC - High Performance Computing 9 Tests
Machine Learning 5 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 2 Tests
Multi-Core 12 Tests
NVIDIA GPU Compute 6 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 3 Tests
Scientific Computing 4 Tests
Server 5 Tests
Server CPU Tests 6 Tests
Single-Threaded 4 Tests
Texture Compression 2 Tests
Vulkan Compute 4 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
1
December 22 2020
  10 Hours, 2 Minutes
2
December 23 2020
  9 Hours, 59 Minutes
3
December 23 2020
  9 Hours, 58 Minutes
Invert Hiding All Results Option
  9 Hours, 59 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):

1

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: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

2

3

Processor: Intel Core i5-6500 @ 3.60GHz (4 Cores), Motherboard: Gigabyte Z170M-D3H-CF (F22f BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 8GB, Disk: 250GB Samsung SSD 850, Graphics: Gigabyte Intel HD 530 3GB (1050MHz), Audio: Realtek ALC892, Monitor: G237HL, Network: Intel I219-V

OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc7daily20200929-generic (x86_64) 20200928, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Core i5 6500 XmasProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolution123Intel Core i5-6500 @ 3.60GHz (4 Cores)Gigabyte Z170M-D3H-CF (F22f BIOS)Intel Xeon E3-1200 v5/E3-15008GB250GB Samsung SSD 850Gigabyte Intel HD 530 3GB (1050MHz)Realtek ALC892G237HLIntel I219-VUbuntu 20.045.9.0-050900rc7daily20200929-generic (x86_64) 20200928GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.8OpenCL 2.1GCC 9.3.0ext41920x1080OpenBenchmarking.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: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1 Python Details- Python 3.8.5Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

123Result OverviewPhoronix Test Suite100%104%108%111%VkResampleRedisBetsy GPU CompressorasmFishoneDNNeSpeak-NG Speech EngineGROMACSCoremarkSQLite SpeedtestLAMMPS Molecular Dynamics SimulatorStockfishTimed MAFFT AlignmentNode.js V8 Web Tooling BenchmarkAI Benchmark Alphayquake2Monkey Audio EncodingsimdjsonOpenVINOBuild2Timed Eigen CompilationCraftyLZ4 CompressionVkFFTNCNNOpus Codec EncodingIndigoBenchTimed HMMer SearchWavPack Audio EncodingBasis Universalrav1eVKMarkNumpy BenchmarkPHPBenchTimed FFmpeg CompilationCLOMP

Core i5 6500 Xmasvkfft: basis: UASTC Level 2 + RDO Post-Processingai-benchmark: Device AI Scoreai-benchmark: Device Training Scoreai-benchmark: Device Inference Scoregromacs: Water Benchmarkbuild2: Time To Compilenumpy: asmfish: 1024 Hash Memory, 26 Depthbasis: UASTC Level 3build-ffmpeg: Time To Compilehmmer: Pfam Database Searchvkmark: 1920 x 1080vkmark: 1280 x 1024ncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetclomp: Static OMP Speeduponednn: Recurrent Neural Network Training - f32 - CPUcoremark: CoreMark Size 666 - Iterations Per Secondbuild-eigen: Time To Compilebasis: ETC1Sbasis: UASTC Level 2onednn: Recurrent Neural Network Inference - f32 - CPUnode-web-tooling: sqlite-speedtest: Timed Time - Size 1,000compress-lz4: 9 - Decompression Speedcompress-lz4: 9 - Compression Speedopenvino: Person Detection 0106 FP32 - CPUopenvino: Person Detection 0106 FP32 - CPUopenvino: Person Detection 0106 FP16 - CPUopenvino: Person Detection 0106 FP16 - CPUstockfish: Total Timecompress-lz4: 3 - Decompression Speedcompress-lz4: 3 - Compression Speedsimdjson: Kostyaopenvino: Face Detection 0106 FP16 - CPUopenvino: Face Detection 0106 FP16 - CPUopenvino: Face Detection 0106 FP32 - CPUopenvino: Face Detection 0106 FP32 - CPUrav1e: 5indigobench: CPU - Bedroomrav1e: 1indigobench: CPU - Supercaropenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUvkresample: 2x - Singleopenvino: Age Gender Recognition Retail 0013 FP32 - CPUopenvino: Age Gender Recognition Retail 0013 FP32 - CPUsimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDrav1e: 6espeak: Text-To-Speech Synthesiscompress-lz4: 1 - Decompression Speedcompress-lz4: 1 - Compression Speedphpbench: PHP Benchmark Suiterav1e: 10betsy: ETC1 - Highestencode-wavpack: WAV To WavPackcrafty: Elapsed Timeencode-ape: WAV To APEonednn: Deconvolution Batch shapes_1d - f32 - CPUencode-opus: WAV To Opus Encoderedis: SETonednn: IP Shapes 1D - f32 - CPUmafft: Multiple Sequence Alignment - LSU RNAbasis: UASTC Level 0onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUredis: LPUSHredis: LPOPredis: SADDredis: GETonednn: IP Shapes 3D - f32 - CPUyquake2: Software CPU - 1920 x 1080lammps: Rhodopsin Proteinonednn: Convolution Batch Shapes Auto - f32 - CPUbetsy: ETC2 RGB - Highestonednn: Deconvolution Batch shapes_3d - f32 - CPUyquake2: OpenGL 3.x - 1920 x 1080yquake2: OpenGL 1.x - 1920 x 10801231290932.00111956255700.473366.374290.248321461185.451164.257130.87461189716.7744.3342.8252.4321.1024.8296.6923.952.5811.507.2910.176.998.0131.1316.7844.3542.8152.4121.0924.8596.7223.962.6011.487.2710.156.957.9931.151.67407.3692339.76052694.71592.21290.8374258.569.8479.0778175.339.826304.450.636201.830.6458665908151.540.790.573760.521.053788.581.050.9270.4310.3201.0921.612364.77563.0651.612333.250.350.530.541.23534.3298287.06932.946043632.75110.80618.144690360113.76612.483610.7521577856.919.3579512.76212.5895.298651392673.462297378.171794550.922147999.510.952087.72.60620.60897.65316.0395283.0287.81290936.52812006265740.469366.596290.378372794185.534164.258131.04461189716.8244.4042.8952.6321.1624.9396.3624.022.5911.537.2910.177.018.0131.2216.7944.4743.0452.6221.1424.9496.4224.042.6011.567.2810.156.988.0131.221.67392.8591213.12396194.65392.27190.8594234.399.8079.8448172.639.716219.770.646199.550.6459065868153.340.710.573759.501.053753.411.050.9270.4320.3211.0891.62334.81486.8561.602348.810.350.520.541.23534.7248234.16912.726043942.75310.69218.156692007113.69612.445010.7331598272.509.2932312.77712.5815.282131400821.831411549.461788107.042013386.6710.592487.52.61520.572415.7196287.3289.01287931.83311936245690.467368.269290.308182398185.423164.273130.99161289716.7844.5643.0952.6621.1225.0396.3224.052.5811.527.2910.136.988.0131.1316.7544.4343.0052.6221.1225.0596.5024.012.5911.507.2810.126.978.0031.111.67381.2292299.10766694.98092.40090.8094228.299.8680.0158156.839.696301.030.636195.670.6458767248152.640.740.573747.781.073782.661.050.9290.4330.321.0911.602340.68487.5071.602326.130.350.520.541.23734.7818295.16922.746042312.75611.06518.133692143513.70612.519810.7541588544.799.3240712.84712.5925.267891378146.831398436.251779981.461999227.2110.100987.22.58720.536715.9078287.0288.0OpenBenchmarking.org

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.112330060090012001500SE +/- 1.20, N = 31290129012871. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.11232004006008001000Min: 1288 / Avg: 1289.67 / Max: 12921. (CXX) g++ options: -O3 -pthread

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-Processing1232004006008001000SE +/- 0.13, N = 3SE +/- 4.57, N = 3SE +/- 0.01, N = 3932.00936.53931.831. (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-Processing123160320480640800Min: 931.85 / Avg: 932 / Max: 932.26Min: 931.87 / Avg: 936.53 / Max: 945.67Min: 931.82 / Avg: 931.83 / Max: 931.851. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

AI Benchmark Alpha

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

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Score12330060090012001500119512001193

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Score123140280420560700625626624

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Score123120240360480600570574569

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 Benchmark1230.10640.21280.31920.42560.532SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 30.4730.4690.4671. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmark12312345Min: 0.47 / Avg: 0.47 / Max: 0.48Min: 0.47 / Avg: 0.47 / Max: 0.47Min: 0.46 / Avg: 0.47 / Max: 0.471. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile12380160240320400SE +/- 0.28, N = 3SE +/- 0.89, N = 3SE +/- 0.75, N = 3366.37366.60368.27
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile12370140210280350Min: 366.1 / Avg: 366.37 / Max: 366.93Min: 365.45 / Avg: 366.6 / Max: 368.35Min: 367.26 / Avg: 368.27 / Max: 369.73

Numpy Benchmark

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

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark12360120180240300SE +/- 0.14, N = 3SE +/- 0.74, N = 3SE +/- 0.35, N = 3290.24290.37290.30
OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark12350100150200250Min: 289.96 / Avg: 290.24 / Max: 290.38Min: 289.34 / Avg: 290.37 / Max: 291.8Min: 289.83 / Avg: 290.3 / Max: 290.98

asmFish

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

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth1232M4M6M8M10MSE +/- 107973.49, N = 3SE +/- 79178.35, N = 3SE +/- 27175.55, N = 3832146183727948182398
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth1231.5M3M4.5M6M7.5MMin: 8109832 / Avg: 8321460.67 / Max: 8464488Min: 8218133 / Avg: 8372794.33 / Max: 8479579Min: 8141170 / Avg: 8182397.67 / Max: 8233683

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 31234080120160200SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3185.45185.53185.421. (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 3123306090120150Min: 185.31 / Avg: 185.45 / Max: 185.67Min: 185.47 / Avg: 185.53 / Max: 185.63Min: 185.36 / Avg: 185.42 / Max: 185.481. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile1234080120160200SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3164.26164.26164.27
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile123306090120150Min: 164.24 / Avg: 164.26 / Max: 164.27Min: 164.18 / Avg: 164.26 / Max: 164.34Min: 164.2 / Avg: 164.27 / Max: 164.37

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 Search123306090120150SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3130.87131.04130.991. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search12320406080100Min: 130.68 / Avg: 130.87 / Max: 131.13Min: 130.88 / Avg: 131.04 / Max: 131.27Min: 130.84 / Avg: 130.99 / Max: 131.211. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

VKMark

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

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1920 x 1080123130260390520650SE +/- 0.58, N = 3SE +/- 0.58, N = 36116116121. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1920 x 1080123110220330440550Min: 610 / Avg: 611 / Max: 612Min: 611 / Avg: 612 / Max: 6131. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1280 x 10241232004006008001000SE +/- 1.76, N = 3SE +/- 1.00, N = 38978978971. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1280 x 1024123160320480640800Min: 894 / Avg: 896.67 / Max: 900Min: 896 / Avg: 897 / Max: 8991. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m12348121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 316.7716.8216.78MIN: 16.69 / MAX: 17.91MIN: 16.74 / MAX: 17.03MIN: 16.68 / MAX: 18.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m12348121620Min: 16.76 / Avg: 16.77 / Max: 16.78Min: 16.81 / Avg: 16.82 / Max: 16.83Min: 16.74 / Avg: 16.78 / Max: 16.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd1231020304050SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 344.3344.4044.56MIN: 44.17 / MAX: 54.22MIN: 44.31 / MAX: 45.14MIN: 44.4 / MAX: 80.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd123918273645Min: 44.32 / Avg: 44.33 / Max: 44.34Min: 44.36 / Avg: 44.4 / Max: 44.45Min: 44.45 / Avg: 44.56 / Max: 44.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny1231020304050SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 342.8242.8943.09MIN: 42.63 / MAX: 44.54MIN: 42.72 / MAX: 43.44MIN: 42.83 / MAX: 43.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny123918273645Min: 42.74 / Avg: 42.82 / Max: 42.9Min: 42.87 / Avg: 42.89 / Max: 42.91Min: 42.98 / Avg: 43.09 / Max: 43.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet501231224364860SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 352.4352.6352.66MIN: 52.11 / MAX: 62.46MIN: 52.36 / MAX: 62.85MIN: 52.44 / MAX: 54.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet501231122334455Min: 52.38 / Avg: 52.43 / Max: 52.52Min: 52.53 / Avg: 52.63 / Max: 52.74Min: 52.63 / Avg: 52.66 / Max: 52.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet123510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 321.1021.1621.12MIN: 21.02 / MAX: 23.28MIN: 21.05 / MAX: 22.23MIN: 21.05 / MAX: 21.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet123510152025Min: 21.08 / Avg: 21.1 / Max: 21.12Min: 21.14 / Avg: 21.16 / Max: 21.17Min: 21.11 / Avg: 21.12 / Max: 21.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18123612182430SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 324.8224.9325.03MIN: 24.72 / MAX: 25.21MIN: 24.82 / MAX: 25.26MIN: 24.92 / MAX: 34.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18123612182430Min: 24.78 / Avg: 24.82 / Max: 24.9Min: 24.91 / Avg: 24.93 / Max: 24.94Min: 25 / Avg: 25.03 / Max: 25.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg1612320406080100SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 396.6996.3696.32MIN: 96.44 / MAX: 99.07MIN: 96.17 / MAX: 106.29MIN: 96.07 / MAX: 101.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg1612320406080100Min: 96.65 / Avg: 96.69 / Max: 96.72Min: 96.3 / Avg: 96.36 / Max: 96.46Min: 96.26 / Avg: 96.32 / Max: 96.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet123612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 323.9524.0224.05MIN: 23.84 / MAX: 24.25MIN: 23.9 / MAX: 24.3MIN: 23.91 / MAX: 34.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet123612182430Min: 23.92 / Avg: 23.95 / Max: 23.98Min: 23.97 / Avg: 24.02 / Max: 24.06Min: 24 / Avg: 24.05 / Max: 24.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface1230.58281.16561.74842.33122.914SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.582.592.58MIN: 2.57 / MAX: 2.69MIN: 2.57 / MAX: 2.65MIN: 2.57 / MAX: 2.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface123246810Min: 2.58 / Avg: 2.58 / Max: 2.59Min: 2.59 / Avg: 2.59 / Max: 2.6Min: 2.58 / Avg: 2.58 / Max: 2.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b01233691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 311.5011.5311.52MIN: 11.45 / MAX: 11.78MIN: 11.48 / MAX: 11.76MIN: 11.45 / MAX: 21.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b01233691215Min: 11.49 / Avg: 11.5 / Max: 11.52Min: 11.53 / Avg: 11.53 / Max: 11.54Min: 11.49 / Avg: 11.52 / Max: 11.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet123246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.297.297.29MIN: 7.21 / MAX: 9.87MIN: 7.24 / MAX: 7.53MIN: 7.23 / MAX: 7.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet1233691215Min: 7.27 / Avg: 7.29 / Max: 7.3Min: 7.29 / Avg: 7.29 / Max: 7.3Min: 7.28 / Avg: 7.29 / Max: 7.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v21233691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.1710.1710.13MIN: 10.1 / MAX: 20.21MIN: 10.1 / MAX: 12.67MIN: 10.08 / MAX: 11.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v21233691215Min: 10.15 / Avg: 10.17 / Max: 10.19Min: 10.14 / Avg: 10.17 / Max: 10.19Min: 10.12 / Avg: 10.13 / Max: 10.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.997.016.98MIN: 6.89 / MAX: 8.47MIN: 6.89 / MAX: 8.2MIN: 6.86 / MAX: 8.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31233691215Min: 6.99 / Avg: 6.99 / Max: 6.99Min: 7 / Avg: 7.01 / Max: 7.02Min: 6.96 / Avg: 6.98 / Max: 71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.018.018.01MIN: 7.9 / MAX: 10.56MIN: 7.92 / MAX: 9.29MIN: 7.92 / MAX: 9.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21233691215Min: 7.98 / Avg: 8.01 / Max: 8.05Min: 8 / Avg: 8.01 / Max: 8.02Min: 8 / Avg: 8.01 / Max: 8.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet123714212835SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 331.1331.2231.13MIN: 30.96 / MAX: 31.38MIN: 31.06 / MAX: 31.55MIN: 30.98 / MAX: 31.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet123714212835Min: 31.07 / Avg: 31.13 / Max: 31.2Min: 31.18 / Avg: 31.22 / Max: 31.25Min: 31.09 / Avg: 31.13 / Max: 31.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m12348121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 316.7816.7916.75MIN: 16.67 / MAX: 17.08MIN: 16.7 / MAX: 17.58MIN: 16.65 / MAX: 18.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m12348121620Min: 16.73 / Avg: 16.78 / Max: 16.81Min: 16.75 / Avg: 16.79 / Max: 16.82Min: 16.72 / Avg: 16.75 / Max: 16.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd1231020304050SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 344.3544.4744.43MIN: 44.21 / MAX: 46.96MIN: 44.29 / MAX: 54.28MIN: 44.35 / MAX: 44.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd123918273645Min: 44.3 / Avg: 44.35 / Max: 44.39Min: 44.43 / Avg: 44.47 / Max: 44.51Min: 44.4 / Avg: 44.43 / Max: 44.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny1231020304050SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 342.8143.0443.00MIN: 42.52 / MAX: 88.54MIN: 42.87 / MAX: 43.54MIN: 42.78 / MAX: 45.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny123918273645Min: 42.7 / Avg: 42.81 / Max: 42.97Min: 42.94 / Avg: 43.04 / Max: 43.18Min: 42.93 / Avg: 43 / Max: 43.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet501231224364860SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 352.4152.6252.62MIN: 52.22 / MAX: 62.55MIN: 52.34 / MAX: 54.88MIN: 52.43 / MAX: 52.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet501231122334455Min: 52.37 / Avg: 52.41 / Max: 52.46Min: 52.55 / Avg: 52.62 / Max: 52.68Min: 52.6 / Avg: 52.62 / Max: 52.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet123510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 321.0921.1421.12MIN: 21 / MAX: 21.21MIN: 21.04 / MAX: 21.38MIN: 21.03 / MAX: 30.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet123510152025Min: 21.08 / Avg: 21.09 / Max: 21.12Min: 21.12 / Avg: 21.14 / Max: 21.19Min: 21.08 / Avg: 21.12 / Max: 21.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18123612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 324.8524.9425.05MIN: 24.73 / MAX: 25.1MIN: 24.84 / MAX: 25.22MIN: 24.88 / MAX: 34.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18123612182430Min: 24.82 / Avg: 24.85 / Max: 24.9Min: 24.93 / Avg: 24.94 / Max: 24.96Min: 25 / Avg: 25.05 / Max: 25.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg1612320406080100SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 396.7296.4296.50MIN: 96.23 / MAX: 106.95MIN: 96.04 / MAX: 98.54MIN: 96.25 / MAX: 106.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg1612320406080100Min: 96.57 / Avg: 96.72 / Max: 96.98Min: 96.17 / Avg: 96.42 / Max: 96.59Min: 96.41 / Avg: 96.5 / Max: 96.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet123612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 323.9624.0424.01MIN: 23.86 / MAX: 25.31MIN: 23.93 / MAX: 34.03MIN: 23.91 / MAX: 26.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet123612182430Min: 23.94 / Avg: 23.96 / Max: 24.01Min: 24.01 / Avg: 24.04 / Max: 24.07Min: 24 / Avg: 24.01 / Max: 24.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface1230.5851.171.7552.342.925SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.602.602.59MIN: 2.57 / MAX: 2.74MIN: 2.58 / MAX: 2.67MIN: 2.57 / MAX: 2.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface123246810Min: 2.59 / Avg: 2.6 / Max: 2.61Min: 2.59 / Avg: 2.6 / Max: 2.6Min: 2.59 / Avg: 2.59 / Max: 2.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b01233691215SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 311.4811.5611.50MIN: 11.41 / MAX: 11.68MIN: 11.49 / MAX: 21.55MIN: 11.43 / MAX: 11.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b01233691215Min: 11.45 / Avg: 11.48 / Max: 11.51Min: 11.52 / Avg: 11.56 / Max: 11.63Min: 11.48 / Avg: 11.5 / Max: 11.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet123246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.277.287.28MIN: 7.23 / MAX: 7.42MIN: 7.23 / MAX: 8.32MIN: 7.23 / MAX: 7.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1233691215Min: 7.26 / Avg: 7.27 / Max: 7.29Min: 7.28 / Avg: 7.28 / Max: 7.29Min: 7.28 / Avg: 7.28 / Max: 7.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v21233691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.1510.1510.12MIN: 10.1 / MAX: 11.59MIN: 10.1 / MAX: 12.67MIN: 10.08 / MAX: 11.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v21233691215Min: 10.14 / Avg: 10.15 / Max: 10.17Min: 10.14 / Avg: 10.15 / Max: 10.17Min: 10.1 / Avg: 10.12 / Max: 10.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 36.956.986.97MIN: 6.86 / MAX: 8.6MIN: 6.87 / MAX: 8.4MIN: 6.86 / MAX: 8.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v31233691215Min: 6.93 / Avg: 6.95 / Max: 6.97Min: 6.93 / Avg: 6.98 / Max: 7.01Min: 6.94 / Avg: 6.97 / Max: 7.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 37.998.018.00MIN: 7.9 / MAX: 9.11MIN: 7.9 / MAX: 9.49MIN: 7.91 / MAX: 9.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v21233691215Min: 7.98 / Avg: 7.99 / Max: 8.02Min: 7.97 / Avg: 8.01 / Max: 8.03Min: 7.98 / Avg: 8 / Max: 8.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet123714212835SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 331.1531.2231.11MIN: 30.97 / MAX: 32.65MIN: 31.02 / MAX: 31.57MIN: 30.95 / MAX: 33.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet123714212835Min: 31.07 / Avg: 31.15 / Max: 31.29Min: 31.16 / Avg: 31.22 / Max: 31.25Min: 31.05 / Avg: 31.11 / Max: 31.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

CLOMP

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

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP Speedup1230.360.721.081.441.8SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.61.61.61. (CC) gcc options: -fopenmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP Speedup123246810Min: 1.6 / Avg: 1.6 / Max: 1.6Min: 1.6 / Avg: 1.6 / Max: 1.6Min: 1.6 / Avg: 1.6 / Max: 1.61. (CC) gcc options: -fopenmp -O3 -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 Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU12316003200480064008000SE +/- 2.99, N = 3SE +/- 2.41, N = 3SE +/- 3.80, N = 37407.367392.857381.22MIN: 7387.72MIN: 7385.41MIN: 7370.781. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU12313002600390052006500Min: 7402.83 / Avg: 7407.36 / Max: 7413Min: 7390.18 / Avg: 7392.85 / Max: 7397.67Min: 7373.64 / Avg: 7381.22 / Max: 7385.591. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second12320K40K60K80K100KSE +/- 895.01, N = 15SE +/- 787.86, N = 12SE +/- 874.87, N = 1592339.7691213.1292299.111. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second12316K32K48K64K80KMin: 86225.48 / Avg: 92339.76 / Max: 98039.22Min: 86016.88 / Avg: 91213.12 / Max: 94809.2Min: 85841.52 / Avg: 92299.11 / Max: 97459.951. (CC) gcc options: -O2 -lrt" -lrt

Timed Eigen Compilation

This test times how long it takes to build all Eigen examples. The Eigen examples are compiled serially. Eigen is a C++ template library for linear algebra. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To Compile12320406080100SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 394.7294.6594.98
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To Compile12320406080100Min: 94.69 / Avg: 94.72 / Max: 94.73Min: 94.6 / Avg: 94.65 / Max: 94.72Min: 94.98 / Avg: 94.98 / Max: 94.99

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: ETC1S12320406080100SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 392.2192.2792.401. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1S12320406080100Min: 92.18 / Avg: 92.21 / Max: 92.24Min: 92.15 / Avg: 92.27 / Max: 92.46Min: 92.34 / Avg: 92.4 / Max: 92.461. (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 212320406080100SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 390.8490.8690.811. (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 212320406080100Min: 90.77 / Avg: 90.84 / Max: 90.94Min: 90.78 / Avg: 90.86 / Max: 90.94Min: 90.79 / Avg: 90.81 / Max: 90.831. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1239001800270036004500SE +/- 17.11, N = 3SE +/- 11.93, N = 3SE +/- 12.19, N = 34258.564234.394228.29MIN: 4223.4MIN: 4217.16MIN: 4211.871. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1237001400210028003500Min: 4224.99 / Avg: 4258.56 / Max: 4281.07Min: 4220.98 / Avg: 4234.39 / Max: 4258.18Min: 4216 / Avg: 4228.29 / Max: 4252.671. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Node.js V8 Web Tooling Benchmark

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

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling Benchmark1233691215SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 39.849.809.861. Nodejs v10.19.0
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling Benchmark1233691215Min: 9.67 / Avg: 9.84 / Max: 9.98Min: 9.73 / Avg: 9.8 / Max: 9.86Min: 9.64 / Avg: 9.86 / Max: 10.051. Nodejs v10.19.0

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,00012320406080100SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 379.0879.8480.021. (CC) gcc options: -O2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,0001231530456075Min: 78.91 / Avg: 79.08 / Max: 79.4Min: 79.75 / Avg: 79.84 / Max: 79.99Min: 79.77 / Avg: 80.02 / Max: 80.31. (CC) gcc options: -O2 -ldl -lz -lpthread

LZ4 Compression

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

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speed1232K4K6K8K10KSE +/- 3.90, N = 3SE +/- 6.11, N = 3SE +/- 8.20, N = 38175.38172.68156.81. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speed12314002800420056007000Min: 8168.7 / Avg: 8175.33 / Max: 8182.2Min: 8164.3 / Avg: 8172.57 / Max: 8184.5Min: 8140.4 / Avg: 8156.8 / Max: 8165.31. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speed123918273645SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 339.8239.7139.691. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speed123816243240Min: 39.8 / Avg: 39.82 / Max: 39.84Min: 39.64 / Avg: 39.71 / Max: 39.85Min: 39.56 / Avg: 39.69 / Max: 39.841. (CC) gcc options: -O3

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: CPU12314002800420056007000SE +/- 32.75, N = 3SE +/- 7.41, N = 3SE +/- 48.35, N = 36304.456219.776301.03
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPU12311002200330044005500Min: 6247.75 / Avg: 6304.45 / Max: 6361.21Min: 6209.48 / Avg: 6219.77 / Max: 6234.16Min: 6219.22 / Avg: 6301.03 / Max: 6386.58

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPU1230.1440.2880.4320.5760.72SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.630.640.63
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPU123246810Min: 0.63 / Avg: 0.63 / Max: 0.64Min: 0.64 / Avg: 0.64 / Max: 0.64Min: 0.63 / Avg: 0.63 / Max: 0.64

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPU12313002600390052006500SE +/- 17.73, N = 3SE +/- 2.55, N = 3SE +/- 3.51, N = 36201.836199.556195.67
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPU12311002200330044005500Min: 6174.47 / Avg: 6201.83 / Max: 6235.06Min: 6196.96 / Avg: 6199.55 / Max: 6204.65Min: 6190.09 / Avg: 6195.67 / Max: 6202.15

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPU1230.1440.2880.4320.5760.72SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.640.640.64
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPU123246810Min: 0.64 / Avg: 0.64 / Max: 0.64Min: 0.64 / Avg: 0.64 / Max: 0.64Min: 0.64 / Avg: 0.64 / Max: 0.64

Stockfish

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

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total Time1231.3M2.6M3.9M5.2M6.5MSE +/- 56096.76, N = 3SE +/- 40231.91, N = 3SE +/- 32753.49, N = 35866590590658658767241. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total Time1231000K2000K3000K4000K5000KMin: 5766719 / Avg: 5866590 / Max: 5960796Min: 5828924 / Avg: 5906586.33 / Max: 5963645Min: 5822154 / Avg: 5876723.67 / Max: 59353931. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

LZ4 Compression

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

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speed1232K4K6K8K10KSE +/- 5.61, N = 3SE +/- 2.71, N = 3SE +/- 4.17, N = 38151.58153.38152.61. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speed12314002800420056007000Min: 8141.5 / Avg: 8151.5 / Max: 8160.9Min: 8149 / Avg: 8153.27 / Max: 8158.3Min: 8147.3 / Avg: 8152.57 / Max: 8160.81. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speed123918273645SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 340.7940.7140.741. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speed123816243240Min: 40.79 / Avg: 40.79 / Max: 40.8Min: 40.62 / Avg: 40.71 / Max: 40.8Min: 40.63 / Avg: 40.74 / Max: 40.811. (CC) gcc options: -O3

simdjson

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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: Kostya1230.12830.25660.38490.51320.6415SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.570.570.571. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: Kostya123246810Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.57 / Avg: 0.57 / Max: 0.571. (CXX) g++ options: -O3 -pthread

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPU1238001600240032004000SE +/- 10.88, N = 3SE +/- 3.34, N = 3SE +/- 2.19, N = 33760.523759.503747.78
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPU1237001400210028003500Min: 3748.75 / Avg: 3760.52 / Max: 3782.26Min: 3752.86 / Avg: 3759.5 / Max: 3763.45Min: 3743.95 / Avg: 3747.78 / Max: 3751.53

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPU1230.24080.48160.72240.96321.204SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.051.051.07
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPU123246810Min: 1.05 / Avg: 1.05 / Max: 1.05Min: 1.05 / Avg: 1.05 / Max: 1.06Min: 1.06 / Avg: 1.07 / Max: 1.07

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPU1238001600240032004000SE +/- 16.72, N = 3SE +/- 4.07, N = 3SE +/- 11.32, N = 33788.583753.413782.66
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPU1237001400210028003500Min: 3756.13 / Avg: 3788.58 / Max: 3811.81Min: 3747.48 / Avg: 3753.41 / Max: 3761.21Min: 3764.75 / Avg: 3782.66 / Max: 3803.61

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPU1230.23630.47260.70890.94521.1815SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.051.051.05
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPU123246810Min: 1.04 / Avg: 1.05 / Max: 1.06Min: 1.05 / Avg: 1.05 / Max: 1.06Min: 1.05 / Avg: 1.05 / Max: 1.05

rav1e

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

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 51230.2090.4180.6270.8361.045SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 30.9270.9270.929
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 5123246810Min: 0.92 / Avg: 0.93 / Max: 0.93Min: 0.92 / Avg: 0.93 / Max: 0.93Min: 0.93 / Avg: 0.93 / Max: 0.93

IndigoBench

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: Bedroom1230.09740.19480.29220.38960.487SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.4310.4320.433
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: Bedroom12312345Min: 0.43 / Avg: 0.43 / Max: 0.43Min: 0.43 / Avg: 0.43 / Max: 0.43Min: 0.43 / Avg: 0.43 / Max: 0.43

rav1e

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

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 11230.07220.14440.21660.28880.361SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.3200.3210.320
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 112312345Min: 0.32 / Avg: 0.32 / Max: 0.32Min: 0.32 / Avg: 0.32 / Max: 0.32Min: 0.32 / Avg: 0.32 / Max: 0.32

IndigoBench

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: Supercar1230.24570.49140.73710.98281.2285SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 31.0921.0891.091
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: Supercar123246810Min: 1.09 / Avg: 1.09 / Max: 1.09Min: 1.08 / Avg: 1.09 / Max: 1.09Min: 1.08 / Avg: 1.09 / Max: 1.1

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: CPU1230.36230.72461.08691.44921.8115SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 31.611.601.60
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU123246810Min: 1.61 / Avg: 1.61 / Max: 1.62Min: 1.6 / Avg: 1.6 / Max: 1.6Min: 1.59 / Avg: 1.6 / Max: 1.61

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU1235001000150020002500SE +/- 14.95, N = 3SE +/- 6.39, N = 3SE +/- 7.37, N = 32364.772334.812340.68
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU123400800120016002000Min: 2334.89 / Avg: 2364.77 / Max: 2380.54Min: 2323.94 / Avg: 2334.81 / Max: 2346.05Min: 2326.39 / Avg: 2340.68 / Max: 2350.96

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Single123120240360480600SE +/- 0.89, N = 3SE +/- 1.30, N = 3SE +/- 2.01, N = 3563.07486.86487.511. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Single123100200300400500Min: 561.38 / Avg: 563.06 / Max: 564.4Min: 484.3 / Avg: 486.86 / Max: 488.51Min: 484.82 / Avg: 487.51 / Max: 491.451. (CXX) g++ options: -O3 -pthread

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU1230.36230.72461.08691.44921.8115SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.611.601.60
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU123246810Min: 1.61 / Avg: 1.61 / Max: 1.62Min: 1.59 / Avg: 1.6 / Max: 1.6Min: 1.6 / Avg: 1.6 / Max: 1.61

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU1235001000150020002500SE +/- 11.27, N = 3SE +/- 4.51, N = 3SE +/- 6.47, N = 32333.252348.812326.13
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU123400800120016002000Min: 2310.84 / Avg: 2333.25 / Max: 2346.48Min: 2343.63 / Avg: 2348.81 / Max: 2357.8Min: 2317.87 / Avg: 2326.13 / Max: 2338.9

simdjson

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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandom1230.07880.15760.23640.31520.394SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.350.350.351. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandom12312345Min: 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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweets1230.11930.23860.35790.47720.5965SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.530.520.521. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweets123246810Min: 0.52 / Avg: 0.53 / Max: 0.53Min: 0.52 / Avg: 0.52 / Max: 0.53Min: 0.52 / Avg: 0.52 / Max: 0.531. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserID1230.12150.2430.36450.4860.6075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.540.540.541. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserID123246810Min: 0.54 / Avg: 0.54 / Max: 0.54Min: 0.54 / Avg: 0.54 / Max: 0.54Min: 0.54 / Avg: 0.54 / Max: 0.541. (CXX) g++ options: -O3 -pthread

rav1e

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

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 61230.27830.55660.83491.11321.3915SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 31.2351.2351.237
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 6123246810Min: 1.23 / Avg: 1.23 / Max: 1.24Min: 1.23 / Avg: 1.23 / Max: 1.24Min: 1.24 / Avg: 1.24 / Max: 1.24

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 Synthesis123816243240SE +/- 0.31, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 434.3334.7234.781. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis123714212835Min: 33.45 / Avg: 34.33 / Max: 34.82Min: 34.64 / Avg: 34.72 / Max: 34.88Min: 34.66 / Avg: 34.78 / Max: 34.841. (CC) gcc options: -O2 -std=c99

LZ4 Compression

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

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speed1232K4K6K8K10KSE +/- 15.44, N = 3SE +/- 8.75, N = 3SE +/- 19.61, N = 38287.08234.18295.11. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speed12314002800420056007000Min: 8256.3 / Avg: 8286.97 / Max: 8305.5Min: 8216.6 / Avg: 8234.1 / Max: 8243Min: 8256.9 / Avg: 8295.07 / Max: 83221. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speed12315003000450060007500SE +/- 12.83, N = 3SE +/- 11.80, N = 3SE +/- 10.01, N = 36932.946912.726922.741. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speed12312002400360048006000Min: 6908.18 / Avg: 6932.94 / Max: 6951.18Min: 6897.89 / Avg: 6912.72 / Max: 6936.04Min: 6902.76 / Avg: 6922.74 / Max: 6933.91. (CC) gcc options: -O3

PHPBench

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

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite123130K260K390K520K650KSE +/- 530.95, N = 3SE +/- 403.85, N = 3SE +/- 721.53, N = 3604363604394604231
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite123100K200K300K400K500KMin: 603686 / Avg: 604363 / Max: 605410Min: 603910 / Avg: 604394 / Max: 605196Min: 602790 / Avg: 604231.33 / Max: 605013

rav1e

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

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 101230.62011.24021.86032.48043.1005SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 32.7512.7532.756
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 10123246810Min: 2.74 / Avg: 2.75 / Max: 2.76Min: 2.75 / Avg: 2.75 / Max: 2.76Min: 2.75 / Avg: 2.76 / Max: 2.76

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highest1233691215SE +/- 0.20, N = 12SE +/- 0.35, N = 12SE +/- 0.04, N = 310.8110.6911.071. (CXX) g++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highest1233691215Min: 8.62 / Avg: 10.81 / Max: 11.2Min: 6.86 / Avg: 10.69 / Max: 11.31Min: 10.99 / Avg: 11.06 / Max: 11.11. (CXX) g++ options: -O3 -O2 -lpthread -ldl

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack12348121620SE +/- 0.06, N = 5SE +/- 0.08, N = 5SE +/- 0.05, N = 518.1418.1618.131. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack123510152025Min: 18.08 / Avg: 18.14 / Max: 18.4Min: 18.07 / Avg: 18.16 / Max: 18.48Min: 18.08 / Avg: 18.13 / Max: 18.321. (CXX) g++ options: -rdynamic

Crafty

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

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time1231.5M3M4.5M6M7.5MSE +/- 12299.78, N = 3SE +/- 8201.00, N = 3SE +/- 9587.81, N = 36903601692007169214351. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time1231.2M2.4M3.6M4.8M6MMin: 6879578 / Avg: 6903601.33 / Max: 6920197Min: 6910213 / Avg: 6920071.33 / Max: 6936353Min: 6905135 / Avg: 6921434.67 / Max: 69383321. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

Monkey Audio Encoding

This test times how long it takes to encode a sample WAV file to Monkey's Audio APE format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APE12348121620SE +/- 0.03, N = 5SE +/- 0.03, N = 5SE +/- 0.04, N = 513.7713.7013.711. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APE12348121620Min: 13.7 / Avg: 13.77 / Max: 13.88Min: 13.64 / Avg: 13.7 / Max: 13.8Min: 13.63 / Avg: 13.71 / Max: 13.841. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU1233691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 312.4812.4512.52MIN: 12.38MIN: 12.35MIN: 12.41. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU12348121620Min: 12.47 / Avg: 12.48 / Max: 12.51Min: 12.42 / Avg: 12.45 / Max: 12.46Min: 12.48 / Avg: 12.52 / Max: 12.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode1233691215SE +/- 0.03, N = 5SE +/- 0.01, N = 5SE +/- 0.03, N = 510.7510.7310.751. (CXX) g++ options: -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode1233691215Min: 10.71 / Avg: 10.75 / Max: 10.87Min: 10.71 / Avg: 10.73 / Max: 10.78Min: 10.72 / Avg: 10.75 / Max: 10.861. (CXX) g++ options: -fvisibility=hidden -logg -lm

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SET123300K600K900K1200K1500KSE +/- 16728.26, N = 7SE +/- 19649.82, N = 3SE +/- 14556.44, N = 31577856.911598272.501588544.791. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SET123300K600K900K1200K1500KMin: 1517450.75 / Avg: 1577856.91 / Max: 1620953Min: 1560411.88 / Avg: 1598272.5 / Max: 1626328.38Min: 1562600 / Avg: 1588544.79 / Max: 1612954.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.01904, N = 3SE +/- 0.01064, N = 3SE +/- 0.01497, N = 39.357959.293239.32407MIN: 9.27MIN: 9.21MIN: 9.221. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1233691215Min: 9.32 / Avg: 9.36 / Max: 9.39Min: 9.27 / Avg: 9.29 / Max: 9.3Min: 9.3 / Avg: 9.32 / Max: 9.351. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Timed MAFFT Alignment

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA1233691215SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 312.7612.7812.851. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA12348121620Min: 12.63 / Avg: 12.76 / Max: 12.92Min: 12.73 / Avg: 12.78 / Max: 12.81Min: 12.79 / Avg: 12.85 / Max: 12.931. (CC) gcc options: -std=c99 -O3 -lm -lpthread

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 01233691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 312.5912.5812.591. (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 012348121620Min: 12.58 / Avg: 12.59 / Max: 12.59Min: 12.57 / Avg: 12.58 / Max: 12.59Min: 12.58 / Avg: 12.59 / Max: 12.61. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1231.19222.38443.57664.76885.961SE +/- 0.00409, N = 3SE +/- 0.00771, N = 3SE +/- 0.00465, N = 35.298655.282135.26789MIN: 5.23MIN: 5.2MIN: 5.191. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810Min: 5.29 / Avg: 5.3 / Max: 5.31Min: 5.27 / Avg: 5.28 / Max: 5.29Min: 5.26 / Avg: 5.27 / Max: 5.281. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSH123300K600K900K1200K1500KSE +/- 11099.37, N = 3SE +/- 6852.68, N = 3SE +/- 19289.08, N = 31392673.461400821.831378146.831. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSH123200K400K600K800K1000KMin: 1379575.12 / Avg: 1392673.46 / Max: 1414744Min: 1392936 / Avg: 1400821.83 / Max: 1414472.38Min: 1340611.25 / Avg: 1378146.83 / Max: 1404629.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOP123500K1000K1500K2000K2500KSE +/- 4519.60, N = 3SE +/- 4433.16, N = 3SE +/- 13945.24, N = 32297378.171411549.461398436.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOP123400K800K1200K1600K2000KMin: 2288842 / Avg: 2297378.17 / Max: 2304221.25Min: 1402749 / Avg: 1411549.46 / Max: 1416883.88Min: 1371830 / Avg: 1398436.25 / Max: 1418984.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADD123400K800K1200K1600K2000KSE +/- 7511.17, N = 3SE +/- 5626.67, N = 3SE +/- 11495.06, N = 31794550.921788107.041779981.461. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADD123300K600K900K1200K1500KMin: 1779530.38 / Avg: 1794550.92 / Max: 1802263Min: 1779587.25 / Avg: 1788107.04 / Max: 1798733.88Min: 1764289.38 / Avg: 1779981.46 / Max: 1802378.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GET123500K1000K1500K2000K2500KSE +/- 13688.88, N = 3SE +/- 18018.77, N = 3SE +/- 13990.74, N = 32147999.502013386.671999227.211. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GET123400K800K1200K1600K2000KMin: 2128340.5 / Avg: 2147999.5 / Max: 2174330.5Min: 1977423 / Avg: 2013386.67 / Max: 2033365.75Min: 1972828.25 / Avg: 1999227.21 / Max: 2020460.621. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 310.9510.5910.10MIN: 10.83MIN: 10.46MIN: 9.981. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215Min: 10.94 / Avg: 10.95 / Max: 10.96Min: 10.57 / Avg: 10.59 / Max: 10.63Min: 10.05 / Avg: 10.1 / Max: 10.131. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

yquake2

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

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 1920 x 108012320406080100SE +/- 0.06, N = 3SE +/- 0.27, N = 3SE +/- 0.41, N = 387.787.587.21. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 1920 x 108012320406080100Min: 87.6 / Avg: 87.7 / Max: 87.8Min: 87 / Avg: 87.53 / Max: 87.9Min: 86.5 / Avg: 87.23 / Max: 87.91. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein1230.58841.17681.76522.35362.942SE +/- 0.008, N = 3SE +/- 0.001, N = 3SE +/- 0.009, N = 32.6062.6152.5871. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein123246810Min: 2.59 / Avg: 2.61 / Max: 2.62Min: 2.61 / Avg: 2.61 / Max: 2.62Min: 2.58 / Avg: 2.59 / Max: 2.61. (CXX) g++ options: -O3 -pthread -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 Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 320.6120.5720.54MIN: 20.5MIN: 20.4MIN: 20.431. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123510152025Min: 20.56 / Avg: 20.61 / Max: 20.65Min: 20.53 / Avg: 20.57 / Max: 20.6Min: 20.52 / Avg: 20.54 / Max: 20.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highest12468107.6531. (CXX) g++ options: -O3 -O2 -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU12348121620SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 316.0415.7215.91MIN: 15.86MIN: 15.52MIN: 15.631. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU12348121620Min: 15.98 / Avg: 16.04 / Max: 16.15Min: 15.64 / Avg: 15.72 / Max: 15.76Min: 15.76 / Avg: 15.91 / Max: 16.121. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

yquake2

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

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 1920 x 108012360120180240300SE +/- 0.82, N = 3SE +/- 1.37, N = 3SE +/- 1.51, N = 3283.0287.3287.01. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 1920 x 108012350100150200250Min: 281.9 / Avg: 283 / Max: 284.6Min: 285.7 / Avg: 287.27 / Max: 290Min: 285.1 / Avg: 287.03 / Max: 2901. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 1.x - Resolution: 1920 x 108012360120180240300SE +/- 0.38, N = 3SE +/- 0.55, N = 3SE +/- 0.78, N = 3287.8289.0288.01. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 1.x - Resolution: 1920 x 108012350100150200250Min: 287.4 / Avg: 287.83 / Max: 288.6Min: 288.1 / Avg: 289.03 / Max: 290Min: 286.4 / Avg: 287.97 / Max: 288.81. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

108 Results Shown

VkFFT
Basis Universal
AI Benchmark Alpha:
  Device AI Score
  Device Training Score
  Device Inference Score
GROMACS
Build2
Numpy Benchmark
asmFish
Basis Universal
Timed FFmpeg Compilation
Timed HMMer Search
VKMark:
  1920 x 1080
  1280 x 1024
NCNN:
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
CLOMP
oneDNN
Coremark
Timed Eigen Compilation
Basis Universal:
  ETC1S
  UASTC Level 2
oneDNN
Node.js V8 Web Tooling Benchmark
SQLite Speedtest
LZ4 Compression:
  9 - Decompression Speed
  9 - Compression Speed
OpenVINO:
  Person Detection 0106 FP32 - CPU:
    ms
    FPS
  Person Detection 0106 FP16 - CPU:
    ms
    FPS
Stockfish
LZ4 Compression:
  3 - Decompression Speed
  3 - Compression Speed
simdjson
OpenVINO:
  Face Detection 0106 FP16 - CPU:
    ms
    FPS
  Face Detection 0106 FP32 - CPU:
    ms
    FPS
rav1e
IndigoBench
rav1e
IndigoBench
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
VkResample
OpenVINO:
  Age Gender Recognition Retail 0013 FP32 - CPU:
    ms
    FPS
simdjson:
  LargeRand
  PartialTweets
  DistinctUserID
rav1e
eSpeak-NG Speech Engine
LZ4 Compression:
  1 - Decompression Speed
  1 - Compression Speed
PHPBench
rav1e
Betsy GPU Compressor
WavPack Audio Encoding
Crafty
Monkey Audio Encoding
oneDNN
Opus Codec Encoding
Redis
oneDNN
Timed MAFFT Alignment
Basis Universal
oneDNN
Redis:
  LPUSH
  LPOP
  SADD
  GET
oneDNN
yquake2
LAMMPS Molecular Dynamics Simulator
oneDNN
Betsy GPU Compressor
oneDNN
yquake2:
  OpenGL 3.x - 1920 x 1080
  OpenGL 1.x - 1920 x 1080

1

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: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 22 December 2020 20:20 by user phoronix.

2

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: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 23 December 2020 05:52 by user phoronix.

3

Processor: Intel Core i5-6500 @ 3.60GHz (4 Cores), Motherboard: Gigabyte Z170M-D3H-CF (F22f BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 8GB, Disk: 250GB Samsung SSD 850, Graphics: Gigabyte Intel HD 530 3GB (1050MHz), Audio: Realtek ALC892, Monitor: G237HL, Network: Intel I219-V

OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc7daily20200929-generic (x86_64) 20200928, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8, OpenCL: OpenCL 2.1, 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: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 23 December 2020 12:41 by user phoronix.