xeon okt

Intel Xeon E5-2609 v4 testing with a MSI X99A RAIDER (MS-7885) v5.0 (P.50 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2210269-NE-XEONOKT7916&grs.

xeon oktProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionABIntel Xeon E5-2609 v4 @ 1.70GHz (8 Cores)MSI X99A RAIDER (MS-7885) v5.0 (P.50 BIOS)Intel Xeon E7 v4/Xeon16GB256GB CORSAIR FORCE LXllvmpipeRealtek ALC892Intel I218-VUbuntu 20.045.9.0-050900rc6daily20200926-generic (x86_64) 20200925GNOME Shell 3.36.2X Server 1.20.83.3 Mesa 20.0.4 (LLVM 9.0.1 256 bits)GCC 9.3.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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,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_cpufreq ondemand - CPU Microcode: 0xb000038Python Details- Python 2.7.18rc1 + Python 3.8.2Security 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: Not affected + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

xeon oktonednn: Recurrent Neural Network Inference - f32 - CPUgraphics-magick: HWB Color Spacegraphics-magick: Rotateaom-av1: Speed 6 Realtime - Bosphorus 4Kclickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cachencnn: CPU - resnet50jpegxl-decode: Allavifenc: 0onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: IP Shapes 3D - f32 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamgraphics-magick: Noise-Gaussianncnn: CPU - yolov4-tinybrl-cad: VGR Performance Metricaom-av1: Speed 6 Realtime - Bosphorus 1080pjpegxl-decode: 1kvazaar: Bosphorus 4K - Very Fastclickhouse: 100M Rows Web Analytics Dataset, Third Rungraphics-magick: Resizingaom-av1: Speed 10 Realtime - Bosphorus 1080pkvazaar: Bosphorus 1080p - Ultra Fastchia-vdf: Square Assembly Optimizedjpegxl: PNG - 90avifenc: 2aom-av1: Speed 6 Two-Pass - Bosphorus 1080pnode-web-tooling: deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamaom-av1: Speed 8 Realtime - Bosphorus 1080pncnn: CPU - resnet18compress-7zip: Decompression Ratingavifenc: 6jpegxl: JPEG - 90aom-av1: Speed 9 Realtime - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 4Konednn: IP Shapes 1D - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUaom-av1: Speed 6 Two-Pass - Bosphorus 4Kncnn: CPU - shufflenet-v2onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUaom-av1: Speed 4 Two-Pass - Bosphorus 4Kncnn: CPU - regnety_400monednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUlammps: Rhodopsin Proteinavifenc: 6, Losslessmnn: resnet-v2-50onednn: IP Shapes 3D - u8s8f32 - CPUncnn: CPU - mobilenetavifenc: 10, Losslessaom-av1: Speed 10 Realtime - Bosphorus 4Kencode-flac: WAV To FLACmnn: mobilenetV3aom-av1: Speed 9 Realtime - Bosphorus 4Kdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamncnn: CPU - squeezenet_ssdclickhouse: 100M Rows Web Analytics Dataset, Second Runncnn: CPU - FastestDetdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamncnn: CPU - vgg16ncnn: CPU-v2-v2 - mobilenet-v2onednn: Recurrent Neural Network Training - f32 - CPUdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streammnn: MobileNetV2_224compress-7zip: Compression Ratingdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionbuild-python: Defaultaom-av1: Speed 4 Two-Pass - Bosphorus 1080pkvazaar: Bosphorus 4K - Ultra Fastmnn: inception-v3ncnn: CPU - alexnetglibc-bench: expdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamchia-vdf: Square Plain C++deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamkvazaar: Bosphorus 1080p - Very Fastbuild-mplayer: Time To Compilemnn: squeezenetv1.1deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamglibc-bench: asinhncnn: CPU-v3-v3 - mobilenet-v3mnn: nasnetncnn: CPU - mnasnetbuild-python: Released Build, PGO + LTO Optimizedonednn: Convolution Batch Shapes Auto - f32 - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUncnn: CPU - vision_transformerglibc-bench: ffsllastcenc: Thoroughonednn: Deconvolution Batch shapes_3d - f32 - CPUbuild-php: Time To Compiledeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streambuild-linux-kernel: allmodconfigbuild-erlang: Time To Compiledeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamblender: BMW27 - CPU-Onlydeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamonednn: Recurrent Neural Network Training - u8s8f32 - CPUastcenc: Mediumbuild-linux-kernel: defconfigmnn: SqueezeNetV1.0deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamonednn: Deconvolution Batch shapes_1d - f32 - CPUncnn: CPU - efficientnet-b0onednn: Convolution Batch Shapes Auto - u8s8f32 - CPUdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUastcenc: Exhaustiveglibc-bench: atanhastcenc: Fastbuild-nodejs: Time To Compilemnn: mobilenet-v1-1.0glibc-bench: log2glibc-bench: ffsglibc-bench: modfglibc-bench: cosbuild-gem5: Time To Compileonednn: IP Shapes 1D - u8s8f32 - CPUglibc-bench: tanhglibc-bench: pthread_onceglibc-bench: sincosglibc-bench: singlibc-bench: sqrtglibc-bench: sinhnatron: Spaceshipncnn: CPU - googlenetncnn: CPU - blazefacegromacs: MPI CPU - water_GMX50_bareaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 0 Two-Pass - Bosphorus 4Kgraphics-magick: Enhancedgraphics-magick: Sharpengraphics-magick: Swirljpegxl: JPEG - 100jpegxl: PNG - 100jpegxl: JPEG - 80jpegxl: PNG - 80onednn: IP Shapes 1D - bf16bf16bf16 - CPUAB4341.023713359.644.6927.4593.25579.1644.340398.171222.64132.62887835.174098121.4415.285.1250.3331265.5638.73778003.35270.47510.825.041512.783647.7511.761511426.9853.2462.3616.738.128578.392343.386.813.505811.8420.484077.017894.492.69940.02840.6773.841823.8718.1624.3452.6162.79923.5123.11051497.935521.5949.868.4110.862419.943150.132755.897.047868.71367.558399.664610.03275.322928118.0026172.693132.30955.4684.48.9754.19.6927.7867384.20742.602754200342.535122.9119.9045.328100.70989.92841.68976.2321.526.68878.59814.165333.799111.4678761.246.0241.886614.6549202.30111.67161.222316.32923885.787293.81830.5363479.3237.486632.73417874.2714.8031311.8277.64616.831415.985413.5317.11722.5933385.60124083.820.185650.253940.45012040.125.77330.67456.0289411.0044102.6531396.8725.6688746.75197.0059554.123388.67818.0315936.51010.917.162.070.4560.150.0571431040.270.273.333.454112.593843459.8143.8027.9994.94588.8424.269218.057732.60542.66447735.614146521.1915.455.1750.8231566.1739.08785003.38272.75310.7351501.101348.111.681521327.1593.2662.7416.638.177298.342613.366.773.52561.8520.594098.737935.852.71339.83740.4883.8596523.9818.07724.2352.8482.81123.4123.2061503.504321.6749.688.4410.825920.001349.987156.057.067890.48368.571599.918710.00725.28722984118.2881172.276732.23455.3414.418.9953.9859.6727.7312383.44882.607854100341.93622.94119.6965.337100.54429.944241.62256.2421.5546.67877.3114.145633.752311.4522760.246.031781.884214.6726202.52911.65861.290316.31113881.579293.50730.5676479.79237.722232.70227866.7914.8165311.5477.6416.818415.973313.5417.10562.5917385.83614081.60.185750.227740.47072039.3955.77130.6646.030911.0009102.6311397.0535.6694746.75527.0056254.125888.67648.0315336.50990.917.162.070.4560.150.0571431040.270.273.333.45OpenBenchmarking.org

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAB90018002700360045004341.024112.59MIN: 4203.37MIN: 4104.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceAB801602403204003713841. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: RotateAB701402102803503353451. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

AOM AV1

Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KAB36912159.609.811. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

ClickHouse

100M Rows Web Analytics Dataset, First Run / Cold Cache

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, First Run / Cold CacheAB102030405044.6943.80MIN: 4.76 / MAX: 6666.67MIN: 4.74 / MAX: 4615.381. ClickHouse server version 22.5.4.19 (official build).

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50AB71421283527.4527.99MIN: 27.29 / MAX: 29.43MIN: 27.87 / MAX: 28.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

JPEG XL Decoding libjxl

CPU Threads: All

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: AllAB2040608010093.2594.94

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 0AB130260390520650579.16588.841. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAB0.97661.95322.92983.90644.8834.340394.26921MIN: 4.21MIN: 4.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAB2468108.171228.05773MIN: 8.15MIN: 8.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAB0.59431.18861.78292.37722.97152.64132.6054

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAB0.59951.1991.79852.3982.99752.62882.6644

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: Noise-GaussianAB2040608010078771. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyAB81624324035.1735.61MIN: 34.61 / MAX: 36.08MIN: 34.51 / MAX: 145.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.6VGR Performance MetricAB9K18K27K36K45K40981414651. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -pthread -ldl -lm

AOM AV1

Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pAB51015202521.4421.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

JPEG XL Decoding libjxl

CPU Threads: 1

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: 1AB4812162015.2815.45

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastAB1.16332.32663.48994.65325.81655.125.171. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

ClickHouse

100M Rows Web Analytics Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Third RunAB112233445550.3350.82MIN: 4.81 / MAX: 7500MIN: 4.97 / MAX: 75001. ClickHouse server version 22.5.4.19 (official build).

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: ResizingAB701402102803503123151. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pAB153045607565.5666.171. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastAB91827364538.7339.081. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Chia Blockchain VDF

Test: Square Assembly Optimized

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.7Test: Square Assembly OptimizedAB20K40K60K80K100K77800785001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

JPEG XL libjxl

Input: PNG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90AB0.76051.5212.28153.0423.80253.353.381. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 2AB60120180240300270.48272.751. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pAB369121510.8210.731. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Node.js V8 Web Tooling Benchmark

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkAB1.1342.2683.4024.5365.675.045.00

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAB300600900120015001512.781501.10

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pAB112233445547.7548.101. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18AB369121511.7611.68MIN: 11.68 / MAX: 12.14MIN: 11.57 / MAX: 13.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingAB3K6K9K12K15K15114152131. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6AB61218243026.9927.161. (CXX) g++ options: -O3 -fPIC -lm

JPEG XL libjxl

Input: JPEG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90AB0.73351.4672.20052.9343.66753.243.261. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pAB142842567062.3662.741. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KAB4812162016.7316.631. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUAB2468108.128578.17729MIN: 8.08MIN: 8.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAB2468108.392348.34261MIN: 8.31MIN: 8.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KAB0.76051.5212.28153.0423.80253.383.361. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2AB2468106.816.77MIN: 6.7 / MAX: 25.84MIN: 6.73 / MAX: 6.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAB0.79331.58662.37993.17323.96653.505813.52560MIN: 3.45MIN: 3.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KAB0.41630.83261.24891.66522.08151.841.851. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mAB51015202520.4820.59MIN: 20.41 / MAX: 20.9MIN: 20.52 / MAX: 21.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAB90018002700360045004077.014098.73MIN: 4074.41MIN: 4092.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAB2K4K6K8K10K7894.497935.85MIN: 7862.58MIN: 7928.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinAB0.61041.22081.83122.44163.0522.6992.7131. (CXX) g++ options: -O3 -pthread -lm -ldl

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6, LosslessAB91827364540.0339.841. (CXX) g++ options: -O3 -fPIC -lm

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50AB91827364540.6840.49MIN: 40.52 / MAX: 58.97MIN: 40.38 / MAX: 59.761. (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

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAB0.86841.73682.60523.47364.3423.841803.85965MIN: 3.81MIN: 3.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetAB61218243023.8723.98MIN: 23.26 / MAX: 24.39MIN: 23.02 / MAX: 46.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 10, LosslessAB4812162018.1618.081. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KAB61218243024.3424.231. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACAB122436486052.6252.851. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3AB0.63251.2651.89752.533.16252.7992.811MIN: 2.77 / MAX: 3.18MIN: 2.79 / MAX: 3.181. (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

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KAB61218243023.5123.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAB61218243023.1123.21

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAB300600900120015001497.941503.50

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdAB51015202521.5921.67MIN: 21.41 / MAX: 42.91MIN: 21.53 / MAX: 23.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

ClickHouse

100M Rows Web Analytics Dataset, Second Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.5.4.19100M Rows Web Analytics Dataset, Second RunAB112233445549.8649.68MIN: 5.13 / MAX: 5000MIN: 4.93 / MAX: 75001. ClickHouse server version 22.5.4.19 (official build).

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetAB2468108.418.44MIN: 8.33 / MAX: 13.21MIN: 8.39 / MAX: 9.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAB369121510.8610.83

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAB51015202519.9420.00

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAB112233445550.1349.99

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16AB132639526555.8956.05MIN: 55.71 / MAX: 57.17MIN: 55.71 / MAX: 75.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2AB2468107.047.06MIN: 6.98 / MAX: 7.12MIN: 7 / MAX: 7.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAB2K4K6K8K10K7868.717890.48MIN: 7860.85MIN: 7887.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAB80160240320400367.56368.57

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAB2040608010099.6699.92

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAB369121510.0310.01

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224AB1.19252.3853.57754.775.96255.3005.287MIN: 5.27 / MAX: 6.53MIN: 5.25 / MAX: 10.121. (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

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingAB5K10K15K20K25K22928229841. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAB306090120150118.00118.29

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAB4080120160200172.69172.28

Parallel BZIP2 Compression

FreeBSD-13.0-RELEASE-amd64-memstick.img Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionAB81624324032.3132.231. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Timed CPython Compilation

Build Configuration: Default

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: DefaultAB122436486055.4755.34

AOM AV1

Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pAB0.99231.98462.97693.96924.96154.404.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastAB36912158.978.991. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3AB122436486054.1053.99MIN: 53.89 / MAX: 101.31MIN: 53.83 / MAX: 73.181. (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

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetAB36912159.699.67MIN: 9.64 / MAX: 9.83MIN: 9.62 / MAX: 9.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Glibc Benchmarks

Benchmark: exp

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: expAB71421283527.7927.731. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAB80160240320400384.21383.45

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAB0.58681.17361.76042.34722.9342.60272.6078

Chia Blockchain VDF

Test: Square Plain C++

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.7Test: Square Plain C++AB12K24K36K48K60K54200541001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAB70140210280350342.54341.94

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Very FastAB51015202522.9022.941. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Timed MPlayer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileAB306090120150119.90119.70

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1AB1.20082.40163.60244.80326.0045.3285.337MIN: 5.29 / MAX: 7.62MIN: 5.31 / MAX: 7.551. (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

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAB20406080100100.71100.54

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAB36912159.92809.9442

Glibc Benchmarks

Benchmark: asinh

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: asinhAB102030405041.6941.621. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3AB2468106.236.24MIN: 6.18 / MAX: 6.3MIN: 6.19 / MAX: 6.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Mobile Neural Network

Model: nasnet

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetAB51015202521.5221.55MIN: 21.31 / MAX: 40.96MIN: 21.33 / MAX: 40.771. (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

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetAB2468106.686.67MIN: 6.59 / MAX: 12.03MIN: 6.61 / MAX: 7.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Timed CPython Compilation

Build Configuration: Released Build, PGO + LTO Optimized

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedAB2004006008001000878.60877.31

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAB4812162014.1714.15MIN: 13.87MIN: 13.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAB81624324033.8033.75

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAB369121511.4711.45MIN: 11.44MIN: 11.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerAB160320480640800761.24760.24MIN: 755.05 / MAX: 780.87MIN: 753.97 / MAX: 772.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Glibc Benchmarks

Benchmark: ffsll

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: ffsllAB2468106.024006.031781. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughAB0.42450.8491.27351.6982.12251.88661.88421. (CXX) g++ options: -O3 -flto -pthread

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAB4812162014.6514.67MIN: 14.63MIN: 14.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompileAB4080120160200202.30202.53

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAB369121511.6711.66

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAB142842567061.2261.29

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAB4812162016.3316.31

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: allmodconfigAB80016002400320040003885.793881.58

Timed Erlang/OTP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 25.0Time To CompileAB60120180240300293.82293.51

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAB71421283530.5430.57

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: BMW27 - Compute: CPU-OnlyAB100200300400500479.30479.79

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAB50100150200250237.49237.72

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAB81624324032.7332.70

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAB2K4K6K8K10K7874.277866.79MIN: 7868.63MIN: 7862.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumAB4812162014.8014.821. (CXX) g++ options: -O3 -flto -pthread

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: defconfigAB70140210280350311.83311.55

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0AB2468107.6467.640MIN: 7.61 / MAX: 10.41MIN: 7.6 / MAX: 8.841. (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

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAB4812162016.8316.82

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAB4812162015.9915.97MIN: 15.86MIN: 15.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0AB369121513.5313.54MIN: 13.48 / MAX: 13.64MIN: 13.49 / MAX: 13.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUAB4812162017.1217.11MIN: 17.04MIN: 17.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAB0.58351.1671.75052.3342.91752.59332.5917

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAB80160240320400385.60385.84

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAB90018002700360045004083.824081.60MIN: 4076.89MIN: 4073.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveAB0.04180.08360.12540.16720.2090.18560.18571. (CXX) g++ options: -O3 -flto -pthread

Glibc Benchmarks

Benchmark: atanh

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: atanhAB112233445550.2550.231. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

ASTC Encoder

Preset: Fast

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: FastAB91827364540.4540.471. (CXX) g++ options: -O3 -flto -pthread

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To CompileAB4008001200160020002040.122039.40

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0AB1.29892.59783.89675.19566.49455.7735.771MIN: 5.74 / MAX: 7.01MIN: 5.73 / MAX: 25.011. (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

Glibc Benchmarks

Benchmark: log2

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: log2AB71421283530.6730.661. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: ffs

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: ffsAB2468106.028946.030901. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: modf

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: modfAB369121511.0011.001. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: cos

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: cosAB20406080100102.65102.631. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To CompileAB300600900120015001396.871397.05

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUAB1.27562.55123.82685.10246.3785.668875.66947MIN: 5.65MIN: 5.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Glibc Benchmarks

Benchmark: tanh

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: tanhAB112233445546.7546.761. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: pthread_once

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: pthread_onceAB2468107.005957.005621. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: sincos

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: sincosAB122436486054.1254.131. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: sin

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: sinAB2040608010088.6888.681. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: sqrt

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: sqrtAB2468108.031598.031531. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Glibc Benchmarks

Benchmark: sinh

OpenBenchmarking.orgns, Fewer Is BetterGlibc BenchmarksBenchmark: sinhAB81624324036.5136.511. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s

Natron

Input: Spaceship

OpenBenchmarking.orgFPS, More Is BetterNatron 2.4.3Input: SpaceshipAB0.20250.4050.60750.811.01250.90.9

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetAB4812162017.1617.16MIN: 17.05 / MAX: 18.6MIN: 17.04 / MAX: 191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceAB0.46580.93161.39741.86322.3292.072.07MIN: 2.04 / MAX: 2.17MIN: 2.04 / MAX: 2.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bareAB0.10260.20520.30780.41040.5130.4560.4561. (CXX) g++ options: -O3 -pthread

AOM AV1

Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pAB0.03380.06760.10140.13520.1690.150.151. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

AOM AV1

Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KAB0.01130.02260.03390.04520.05650.050.051. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedAB163248648071711. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenAB102030405043431. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SwirlAB204060801001041041. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

JPEG XL libjxl

Input: JPEG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100AB0.06080.12160.18240.24320.3040.270.271. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

JPEG XL libjxl

Input: PNG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 100AB0.06080.12160.18240.24320.3040.270.271. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

JPEG XL libjxl

Input: JPEG - Quality: 80

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 80AB0.74931.49862.24792.99723.74653.333.331. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

JPEG XL libjxl

Input: PNG - Quality: 80

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 80AB0.77631.55262.32893.10523.88153.453.451. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

Phoronix Test Suite v10.8.4