2888

Intel Xeon E E-2488 testing with a Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2403223-NE-28881544411&gru.

2888ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionabcdIntel Xeon E E-2488 @ 3.20GHz (8 Cores / 16 Threads)Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS)Intel Device 7a272 x 32GB DRAM-4400MT/s Micron MTC20C2085S1EC48BA1960GB Micron_7450_MTFDKBA960TFR + 3201GB Micron_7450_MTFDKCC3T2TFSllvmpipeVE2282 x Intel I210Ubuntu 22.046.2.0-26-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.44.5 Mesa 23.0.4-0ubuntu1~22.04.1 (LLVM 15.0.7 256 bits)1.3.238GCC 11.4.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x11f - Thermald 2.4.9 Python Details- Python 3.10.12Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

2888quicksilver: CTS2quicksilver: CORAL2 P1quicksilver: CORAL2 P2openvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080pospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timeospray: particle_volume/pathtracer/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/pathtracer/real_timedeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamcompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingstockfish: Chess Benchmarkgromacs: MPI CPU - water_GMX50_barenamd: ATPase with 327,506 Atomsnamd: STMV with 1,066,628 Atomsrocksdb: Overwriterocksdb: Rand Fillrocksdb: Rand Readrocksdb: Update Randrocksdb: Seq Fillrocksdb: Rand Fill Syncrocksdb: Read While Writingrocksdb: Read Rand Write Randspeedb: Rand Fillspeedb: Rand Readspeedb: Update Randspeedb: Seq Fillspeedb: Rand Fill Syncspeedb: Read While Writingspeedb: Read Rand Write Randbrl-cad: VGR Performance Metricv-ray: CPUonednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUospray-studio: 2 - 4K - 1 - Path Tracer - CPUospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUospray-studio: 1 - 4K - 32 - Path Tracer - CPUospray-studio: 2 - 4K - 16 - Path Tracer - CPUospray-studio: 2 - 4K - 32 - Path Tracer - CPUospray-studio: 3 - 4K - 16 - Path Tracer - CPUospray-studio: 3 - 4K - 32 - Path Tracer - CPUospray-studio: 1 - 1080p - 1 - Path Tracer - CPUospray-studio: 2 - 1080p - 1 - Path Tracer - CPUospray-studio: 3 - 1080p - 1 - Path Tracer - CPUospray-studio: 1 - 1080p - 16 - Path Tracer - CPUospray-studio: 1 - 1080p - 32 - Path Tracer - CPUospray-studio: 2 - 1080p - 16 - Path Tracer - CPUospray-studio: 2 - 1080p - 32 - Path Tracer - CPUospray-studio: 3 - 1080p - 16 - Path Tracer - CPUospray-studio: 3 - 1080p - 32 - Path Tracer - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streambuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigprimesieve: 1e12primesieve: 1e13blender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyabcd1293000013320000190000002.6729.0329.09242.6710.78815.1993.39502.11272.341638.8217.3833.551036.92384.46523.93154.02441.478604.26180.5421993.114.31435.453115.906116.36216.2134.857531.292644.3266.0055.96546163.1012.789742.654583.870779.14919.2711341.0447259.5447110.52799.5916814.3312686.15785.08278.0241111.25799.554455.236553.621879.556368.672611.215410.6449156.1413102.80219.07499.2619664267998177766921.4050.673830.20897148572414496255672466394080120013452062552258480223646088318060086996741879105720323280329868682449782187668203092.895867.845336.424397.187964.540992817.811487.6495699730113511558443105331578353159951846023677332412245428584068679824412358083048103936321500.07137.78137.4716.47370.269.842.8115.9229.364.8836.78119.27.7110.3915.251.9218.110.9344.30.36437.1893107.856911.71593.848536.179610.03534.89811.4526779.3582124.607635.942510.038672.404318.644150.269414.5578356.627993.927225.6029.7178440.7639107.974393.0261310.07720.268245.051123.28336.89165.691295.39414.081292000012430000187000002.6728.9129.74238.9810.71816.6697.98502.15271.841635.4213.6433.511052.53383.87528.03153.23440.948497.74181.2821852.434.29634.857115.017103.48915.971135.94531.969642.6665.989885.95732163.0012.809952.681633.873078.93759.1535335.6214260.9455110.128799.534817.8716687.0625.09788.035109.508399.548755.349253.916179.424668.9711.186710.6742151.1466102.61238.99569.18679732367818168951561.4060.673820.2095214681491468080573667339288892076954205948225239722197808833756030708973669886318423117729920412396499188736204742.809987.83926.425386.443954.537632811.371485.1895789720113281562713105941586593149651840463673762415244828604084979976413828054448081943091499.89138.36134.4616.73372.989.7940.815.9229.424.8937.43119.347.610.4115.0852.1918.130.9444.110.36447.5375109.241911.90633.827936.309910.04054.87631.4499777.0222124.439836.515510.039872.255918.543150.353214.4952357.545293.668726.44899.7363444.6478108.847293.2281310.86321.056246.008124.06335.93166.181300.83413.331290000013410000184600002.6629.6429.17239.6610.59809.3991.07499.31275.681626.27219.2233.721039.07385.24524.06154.34437.878581.04180.4821956.684.31735.323106.976116.11516.227136.516534.965643.9455.98925.93355162.4932.807822.709943.864529.00939.1718334.361260.4541109.651599.5805805.7857676.40095.10168.0302109.034299.512354.920653.589379.745768.846311.22610.667152.4416102.3839.01839.27129715967661174089861.4080.673340.20891145205614665795749208092939620423552066352374402220254787558359761930743285104559423166431654972405977188971203592.90027.843776.435536.030524.545412808.21487.0595689722113281563663104581579633150161844233672352413244828574075979629415608051747805935661502.74134.9137.0716.68377.29.8743.916.01294.9236.47118.67.6910.3715.251.8118.260.9344.30.36443.9691109.024611.95043.834536.468310.03684.95021.4736776.5215124.513636.674810.043272.820718.655650.149614.521356.29193.732126.22379.7584443.5299107.854192.6221308.27920.539242.435123.13336.35164.961294.93414.521268000013400000187300002.6628.9628.76239.7810.62778.9586.33494.26273.911649.85214.6233.551047.18384.29522.81154.54433.488570.68183.0621874.684.435.927116.365109.27115.927120.657530.366639.3965.999035.96271163.0882.823082.714913.866179.0649.2635339.1941264.1219110.532999.6773822.157683.35085.08938.0335110.855299.657955.33453.767579.488568.890411.230410.6192153.7216104.3478.98619.33619704467622170150351.4050.658440.20937145542314472905638508193921820088462063502392670220230788077758376227734814106476923239230365562421096188430203262.812567.847346.406916.674694.533152814.221487.1995789727113271562653104091583203156011840063666812414244828584064179324409698039547474935431501.44138.1139.0716.67376.5110.2646.316.1829.194.8437.26119.227.6310.415.2351.7418.440.9343.680.36441.2935107.94611.78063.781536.177910.02634.85111.458778.3346124.464136.072810.028772.276218.593850.312914.5116356.152394.155126.00519.5744445.1168107.10691.8371308.97619.962242.189122.49336.1166.341294.63413.9OpenBenchmarking.org

Quicksilver

Input: CTS2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2abcd3M6M9M12M15M129300001292000012900000126800001. (CXX) g++ options: -fopenmp -O3 -march=native

Quicksilver

Input: CORAL2 P1

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1abcd3M6M9M12M15M133200001243000013410000134000001. (CXX) g++ options: -fopenmp -O3 -march=native

Quicksilver

Input: CORAL2 P2

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2abcd4M8M12M16M20M190000001870000018460000187300001. (CXX) g++ options: -fopenmp -O3 -march=native

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabcd0.60081.20161.80242.40323.0042.672.672.662.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabcd71421283529.0328.9129.6428.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabcd71421283529.0929.7429.1728.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabcd50100150200250242.67238.98239.66239.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabcd369121510.7810.7110.5910.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabcd2004006008001000815.19816.66809.39778.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabcd2040608010093.3997.9891.0786.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabcd110220330440550502.11502.15499.31494.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabcd60120180240300272.34271.84275.68273.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabcd4008001200160020001638.801635.401626.271649.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd50100150200250217.38213.64219.22214.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabcd81624324033.5533.5133.7233.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd20040060080010001036.921052.531039.071047.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd80160240320400384.46383.87385.24384.291. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd110220330440550523.93528.03524.06522.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabcd306090120150154.02153.23154.34154.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabcd100200300400500441.47440.94437.87433.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd2K4K6K8K10K8604.268497.748581.048570.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd4080120160200180.54181.28180.48183.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd5K10K15K20K25K21993.1121852.4321956.6821874.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kabcd0.991.982.973.964.954.3144.2964.3174.4001. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kabcd81624324035.4534.8635.3235.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kabcd306090120150115.91115.02106.98116.371. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kabcd306090120150116.36103.49116.12109.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pabcd4812162016.2015.9716.2315.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pabcd306090120150134.86135.94136.52120.661. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pabcd120240360480600531.29531.97534.97530.371. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pabcd140280420560700644.33642.67643.95639.401. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeabcd2468106.005005.989885.989205.99903

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeabcd1.34222.68444.02665.36886.7115.965465.957325.933555.96271

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeabcd4080120160200163.10163.00162.49163.09

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeabcd0.63521.27041.90562.54083.1762.789742.809952.807822.82308

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeabcd0.61091.22181.83272.44363.05452.654582.681632.709942.71491

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeabcd0.87141.74282.61423.48564.3573.870773.873073.864523.86617

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd36912159.14918.93759.00939.0640

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd36912159.27119.15359.17189.2635

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd70140210280350341.04335.62334.36339.19

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd60120180240300259.54260.95260.45264.12

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd20406080100110.53110.13109.65110.53

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd2040608010099.5999.5399.5899.68

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd2004006008001000814.33817.87805.79822.16

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd150300450600750686.16687.06676.40683.35

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabcd1.14792.29583.44374.59165.73955.08275.09785.10165.0893

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabcd2468108.02418.03508.03028.0335

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd20406080100111.26109.51109.03110.86

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd2040608010099.5599.5599.5199.66

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd122436486055.2455.3554.9255.33

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd122436486053.6253.9253.5953.77

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd2040608010079.5679.4279.7579.49

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd153045607568.6768.9768.8568.89

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd369121511.2211.1911.2311.23

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd369121510.6410.6710.6710.62

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd306090120150156.14151.15152.44153.72

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd20406080100102.80102.61102.38104.35

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd36912159.07498.99569.01838.9861

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd36912159.26109.18679.27129.3361

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingabcd20K40K60K80K100K966429732397159970441. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingabcd15K30K45K60K75K679986781867661676221. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess Benchmarkabcd4M8M12M16M20M177766921689515617408986170150351. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareabcd0.31680.63360.95041.26721.5841.4051.4061.4081.4051. (CXX) g++ options: -O3 -lm

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 Atomsabcd0.15160.30320.45480.60640.7580.673830.673820.673340.65844

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 Atomsabcd0.04710.09420.14130.18840.23550.208970.209520.208910.20937

RocksDB

Test: Overwrite

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Overwriteabcd300K600K900K1200K1500K14857241468149145205614554231. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fillabcd300K600K900K1200K1500K14496251468080146657914472901. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readabcd12M24M36M48M60M567246635736673357492080563850811. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randomabcd200K400K600K800K1000K9408019288899293969392181. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Sequential Fillabcd400K800K1200K1600K2000K20013452076954204235520088461. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill Syncabcd40K80K120K160K200K2062552059482066352063501. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingabcd500K1000K1500K2000K2500K22584802252397237440223926701. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomabcd500K1000K1500K2000K2500K22364602219780220254722023071. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fillabcd200K400K600K800K1000K8831808833758755838807771. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Readabcd13M26M39M52M65M600869966030708959761930583762271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update Randomabcd160K320K480K640K800K7418797366987432857348141. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Sequential Fillabcd200K400K600K800K1000K1057203863184104559410647691. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fill Syncabcd50K100K150K200K250K2328032311772316642323921. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While Writingabcd700K1400K2100K2800K3500K29868682992041316549730365561. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Speedb

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write Randomabcd500K1000K1500K2000K2500K24497822396499240597724210961. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance Metricabcd40K80K120K160K200K1876681887361889711884301. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUabcd4K8K12K16K20K20309204742035920326

oneDNN

Harness: IP Shapes 1D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUabcd0.65251.3051.95752.613.26252.895862.809982.900202.81256MIN: 2.67MIN: 2.26MIN: 2.68MIN: 2.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 3D - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUabcd2468107.845337.839207.843777.84734MIN: 7.81MIN: 7.8MIN: 7.8MIN: 7.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUabcd2468106.424396.425386.435536.40691MIN: 6.36MIN: 6.36MIN: 6.37MIN: 6.371. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUabcd2468107.187966.443956.030526.67469MIN: 3.96MIN: 3.88MIN: 3.86MIN: 4.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUabcd1.02272.04543.06814.09085.11354.540994.537634.545414.53315MIN: 4.52MIN: 4.52MIN: 4.53MIN: 4.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Training - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUabcd60012001800240030002817.812811.372808.202814.22MIN: 2806.13MIN: 2799.48MIN: 2797.01MIN: 2802.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUabcd300600900120015001487.641485.181487.051487.19MIN: 1477.71MIN: 1474.21MIN: 1477.55MIN: 1477.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd2K4K6K8K10K9569957895689578

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd2K4K6K8K10K9730972097229727

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd2K4K6K8K10K11351113281132811327

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd30K60K90K120K150K155844156271156366156265

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd70K140K210K280K350K310533310594310458310409

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd30K60K90K120K150K157835158659157963158320

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd70K140K210K280K350K315995314965315016315601

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd40K80K120K160K200K184602184046184423184006

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd80K160K240K320K400K367733367376367235366681

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd50010001500200025002412241524132414

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd50010001500200025002454244824482448

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUabcd60012001800240030002858286028572858

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd9K18K27K36K45K40686408494075940641

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100K79824799767962979324

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd9K18K27K36K45K41235413824156040969

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100K80830805448051780395

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUabcd10K20K30K40K50K48103480814780547474

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUabcd20K40K60K80K100K93632943099356693543

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabcd300600900120015001500.071499.891502.741501.44MIN: 1182.11 / MAX: 1680.75MIN: 1179.88 / MAX: 1674.65MIN: 1180.43 / MAX: 1615.47MIN: 1178.14 / MAX: 1634.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabcd306090120150137.78138.36134.90138.10MIN: 113.8 / MAX: 223.99MIN: 112.35 / MAX: 208.82MIN: 115.43 / MAX: 187.53MIN: 115.79 / MAX: 222.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabcd306090120150137.47134.46137.07139.07MIN: 115.85 / MAX: 217.31MIN: 113.8 / MAX: 201.17MIN: 114.71 / MAX: 226.89MIN: 116.24 / MAX: 219.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabcd4812162016.4716.7316.6816.67MIN: 7.97 / MAX: 25.24MIN: 11.82 / MAX: 45.31MIN: 9.11 / MAX: 50.09MIN: 9 / MAX: 53.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabcd80160240320400370.26372.98377.20376.51MIN: 283.49 / MAX: 524.37MIN: 281.79 / MAX: 526.67MIN: 285.21 / MAX: 479.42MIN: 284.44 / MAX: 525.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabcd36912159.809.799.8710.26MIN: 6.12 / MAX: 36.26MIN: 6.41 / MAX: 38.95MIN: 6.06 / MAX: 39.79MIN: 5.16 / MAX: 34.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabcd102030405042.8140.8043.9046.30MIN: 32.46 / MAX: 50.96MIN: 16.82 / MAX: 52.81MIN: 31.33 / MAX: 53.09MIN: 19.55 / MAX: 53.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabcd4812162015.9215.9216.0116.18MIN: 10.19 / MAX: 56.15MIN: 10.24 / MAX: 55.12MIN: 10.09 / MAX: 56.58MIN: 10.16 / MAX: 60.61. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabcd71421283529.3629.4229.0029.19MIN: 15.65 / MAX: 83.22MIN: 15.68 / MAX: 85.77MIN: 15.36 / MAX: 75.66MIN: 15.64 / MAX: 77.791. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabcd1.1072.2143.3214.4285.5354.884.894.924.84MIN: 3.58 / MAX: 23.42MIN: 3.47 / MAX: 23.33MIN: 3.55 / MAX: 24.13MIN: 3.29 / MAX: 23.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabcd91827364536.7837.4336.4737.26MIN: 27.1 / MAX: 93.52MIN: 26.59 / MAX: 83.53MIN: 26.59 / MAX: 94.27MIN: 26.4 / MAX: 951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabcd306090120150119.20119.34118.60119.22MIN: 90.34 / MAX: 220.76MIN: 91.54 / MAX: 206.51MIN: 92.28 / MAX: 205.27MIN: 90.11 / MAX: 225.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabcd2468107.717.607.697.63MIN: 5.4 / MAX: 34.65MIN: 5.28 / MAX: 31.11MIN: 3.6 / MAX: 34.51MIN: 4.81 / MAX: 36.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabcd369121510.3910.4110.3710.40MIN: 6.23 / MAX: 30.2MIN: 6.28 / MAX: 28.53MIN: 6.3 / MAX: 33.94MIN: 6.06 / MAX: 37.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabcd4812162015.2015.0815.2015.23MIN: 9.51 / MAX: 54.41MIN: 11.22 / MAX: 48.52MIN: 9.34 / MAX: 56.08MIN: 11.43 / MAX: 46.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabcd122436486051.9252.1951.8151.74MIN: 35.62 / MAX: 120.48MIN: 39.05 / MAX: 127.56MIN: 39.16 / MAX: 119.83MIN: 39.4 / MAX: 103.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabcd51015202518.1118.1318.2618.44MIN: 9.91 / MAX: 54.39MIN: 9.61 / MAX: 57.54MIN: 9.63 / MAX: 63.68MIN: 9.76 / MAX: 47.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabcd0.21150.4230.63450.8461.05750.930.940.930.93MIN: 0.48 / MAX: 9.25MIN: 0.48 / MAX: 9.96MIN: 0.47 / MAX: 9.58MIN: 0.56 / MAX: 13.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabcd102030405044.3044.1144.3043.68MIN: 32.51 / MAX: 109.66MIN: 32.5 / MAX: 99.14MIN: 31.6 / MAX: 110.49MIN: 32.82 / MAX: 111.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabcd0.0810.1620.2430.3240.4050.360.360.360.36MIN: 0.19 / MAX: 26.87MIN: 0.22 / MAX: 3.74MIN: 0.2 / MAX: 8.11MIN: 0.22 / MAX: 3.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabcd100200300400500437.19447.54443.97441.29

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabcd20406080100107.86109.24109.02107.95

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd369121511.7211.9111.9511.78

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.86591.73182.59773.46364.32953.84853.82793.83453.7815

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabcd81624324036.1836.3136.4736.18

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabcd369121510.0410.0410.0410.03

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd1.11382.22763.34144.45525.5694.89814.87634.95024.8511

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabcd0.33160.66320.99481.32641.6581.45261.44991.47361.4580

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabcd2004006008001000779.36777.02776.52778.33

Neural Magic DeepSparse

Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabcd306090120150124.61124.44124.51124.46

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabcd81624324035.9436.5236.6736.07

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabcd369121510.0410.0410.0410.03

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd163248648072.4072.2672.8272.28

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabcd51015202518.6418.5418.6618.59

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabcd112233445550.2750.3550.1550.31

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabcd4812162014.5614.5014.5214.51

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabcd80160240320400356.63357.55356.29356.15

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabcd2040608010093.9393.6793.7394.16

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabcd61218243025.6026.4526.2226.01

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabcd36912159.71789.73639.75849.5744

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabcd100200300400500440.76444.65443.53445.12

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabcd20406080100107.97108.85107.85107.11

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigabcd2040608010093.0393.2392.6291.84

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigabcd300600900120015001310.081310.861308.281308.98

Primesieve

Length: 1e12

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12abcd51015202520.2721.0620.5419.961. (CXX) g++ options: -O3

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13abcd50100150200250245.05246.01242.44242.191. (CXX) g++ options: -O3

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-Onlyabcd306090120150123.28124.06123.13122.49

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-Onlyabcd70140210280350336.89335.93336.35336.10

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-Onlyabcd4080120160200165.69166.18164.96166.34

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-Onlyabcd300600900120015001295.391300.831294.931294.63

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-Onlyabcd90180270360450414.08413.33414.52413.90

Phoronix Test Suite v10.8.4