11900K

Intel Core i9-11900K testing with a ASUS ROG MAXIMUS XIII HERO (1402 BIOS) and ASUS Intel RKL GT1 31GB on Ubuntu 21.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2210172-PTS-11900K8800&grs&rdt.

11900KProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionRBCIntel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads)ASUS ROG MAXIMUS XIII HERO (1402 BIOS)Intel Tiger Lake-H32GB2000GB Corsair Force MP600ASUS Intel RKL GT1 31GB (1300MHz)Intel Tiger Lake-H HD AudioASUS MG28U2 x Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 21.105.19.0-rc2-mmio-stale-data-patched (x86_64)GNOME Shell 40.5X Server 1.20.13 + Wayland4.6 Mesa 22.2.0-devel (git-fd27d51 2022-06-15 impish-oibaf-ppa)1.3.217GCC 11.2.0ext43840x2160OpenBenchmarking.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-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x53 - Thermald 2.4.6 Python Details- Python 3.9.7Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + 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 + srbds: Not affected + tsx_async_abort: Not affected

11900Konednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUaom-av1: Speed 6 Realtime - Bosphorus 1080paom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Konednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUjpegxl-decode: Allopenradioss: INIVOL and Fluid Structure Interaction Drop Containeropenradioss: Rubber O-Ring Seal Installationopenradioss: Cell Phone Drop Testaom-av1: Speed 8 Realtime - Bosphorus 4Kspacy: en_core_web_trfy-cruncher: 1Bonednn: Convolution Batch Shapes Auto - f32 - CPUtensorflow: CPU - 16 - AlexNetonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUtensorflow: CPU - 32 - AlexNetonednn: Deconvolution Batch shapes_1d - f32 - CPUtensorflow: CPU - 16 - GoogLeNetjpegxl: JPEG - 100y-cruncher: 500Mjpegxl-decode: 1aom-av1: Speed 10 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080ptensorflow: CPU - 512 - AlexNetonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUavifenc: 6aom-av1: Speed 6 Realtime - Bosphorus 4Konednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUtensorflow: CPU - 256 - AlexNetquadray: 5 - 1080ptensorflow: CPU - 32 - GoogLeNetaom-av1: Speed 8 Realtime - Bosphorus 1080pjpegxl: PNG - 90onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUjpegxl: JPEG - 80jpegxl: PNG - 100jpegxl: PNG - 80tensorflow: CPU - 64 - AlexNetquadray: 5 - 4Kjpegxl: JPEG - 90quadray: 1 - 1080ponednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamtensorflow: CPU - 512 - GoogLeNetdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamonednn: IP Shapes 1D - bf16bf16bf16 - CPUaom-av1: Speed 6 Two-Pass - Bosphorus 4Ktensorflow: CPU - 256 - GoogLeNetquadray: 2 - 1080ptensorflow: CPU - 256 - ResNet-50quadray: 3 - 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 4Ktensorflow: CPU - 64 - GoogLeNetspacy: en_core_web_lgdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamtensorflow: CPU - 16 - ResNet-50avifenc: 10, Losslessdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamquadray: 1 - 4Kavifenc: 0onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUaom-av1: Speed 6 Two-Pass - Bosphorus 1080pdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamopenradioss: Bumper Beamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamtensorflow: CPU - 64 - ResNet-50deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamavifenc: 6, Losslessdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamaom-av1: Speed 4 Two-Pass - Bosphorus 1080pdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamtensorflow: CPU - 32 - ResNet-50openradioss: Bird Strike on Windshieldquadray: 2 - 4Kdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamavifenc: 2quadray: 3 - 1080pdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 0 Two-Pass - Bosphorus 4KRBC5.6889111.31690.9268323.283971991.41980.741991.264.712543427.383408.793439.774.8337768.5360.560.141.41208231.22773.23240.12123.0946.37172049.2614.258179.9717.7088111.348.6970262.790.8422.11160.65150.57148.9174.511.96317.01333.781.26054164.343.7364.11123.8710.333.204910.180.8610.53135.480.951053.453.47145133.74477.469467.9725.343157.734535.250828.36238.5983612.0967.0214.122.193.26.6665.221554114.57168.603919.985.054441.46279.060514.14144.9750.82991541.5433.6872171.699.222922.0222.899243.653710.701111.4388.97316.87109.95429.094221.3308.063.7441.573596.203178.421950.994568.72512.2681.099149.310416.173349.85620.04820.152936.3843109.91840.670.224.071558.460420.7037542.499761733.251681.811648.953.986522911.632903.363006.684.3333673.4263.8664.081.49412243.61774.07250.66118.7348.04171247.79313.902982.2417.3107114.358.4722164.340.8521.661.64154.03151.77175.4111.75566.89334.381.28257163.343.7965.12125.5410.473.1748210.30.8710.65137.020.9410.153.383.50041133.50367.48368.1525.143158.98535.4928.17138.5334612.1766.914.0122.333.226.765.611561114.486869.00220.095.027440.46679.08114.21144.9060.8261241.65433.9521170.999.217322.1122.985143.491710.662111.03939.005216.93110.32679.063521.36307.353.7441.490396.395678.570750.898668.61612.2881.195249.252616.157449.884820.035920.138836.3796109.93460.670.224.230348.535630.7139512.578211630.411631.251663.434.006892989.272994.422946.724.3320971.2564.5463.061.49436242.12740.95247.38118.2847.96177347.89113.858182.2617.2384113.818.5750463.920.8321.60762.07152.96152.17171.6811.73467.02534.41.2827161.553.7764.76125.6110.43.1643610.290.8610.62136.630.9410.0852.983.49109134.58947.42367.6125.3071157.958735.52228.14638.5386812.1366.5914.0622.23.26.6965.361563314.487569.0013205.033439.159.108214.17145.5770.82611341.68435.4639171.239.185322.0622.981743.498610.665111.07959.002116.92110.27689.067621.32308.193.7341.515696.337578.568450.900168.60212.2681.189549.25616.15949.90520.028420.142236.3916109.89930.670.22OpenBenchmarking.org

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPURBC1.282.563.845.126.45.688914.071554.23034MIN: 5.13MIN: 3.75MIN: 3.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: f32 - Engine: CPURBC369121511.316908.460428.53563MIN: 11.25MIN: 8.36MIN: 8.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPURBC0.20850.4170.62550.8341.04250.9268320.7037540.713951MIN: 0.88MIN: 0.66MIN: 0.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPURBC0.73891.47782.21672.95563.69453.283972.499762.57821MIN: 3.23MIN: 2.46MIN: 2.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC4008001200160020001991.401733.251630.41MIN: 1987.75MIN: 1728.72MIN: 1625.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC4008001200160020001980.741681.811631.25MIN: 1976.66MIN: 1676.74MIN: 1625.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC4008001200160020001991.261648.951663.43MIN: 1987.58MIN: 1643.89MIN: 1651.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -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: CPURBC1.06032.12063.18094.24125.30154.712543.986524.00689MIN: 4.58MIN: 3.87MIN: 3.891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC70014002100280035003427.382911.632989.27MIN: 3420.26MIN: 2897.38MIN: 2981.631. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC70014002100280035003408.792903.362994.42MIN: 3402.96MIN: 2897.58MIN: 2987.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC70014002100280035003439.773006.682946.72MIN: 3434.88MIN: 3000.78MIN: 2940.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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: CPURBC1.08762.17523.26284.35045.4384.833774.333364.33209MIN: 4.71MIN: 4.23MIN: 4.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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 1080pRBC163248648068.5373.4271.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -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 4KRBC142842567060.5063.8664.541. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 4KRBC142842567060.1464.0863.061. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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: CPURBC0.33620.67241.00861.34481.6811.412081.494121.49436MIN: 1.35MIN: 1.41MIN: 1.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

JPEG XL Decoding libjxl

CPU Threads: All

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: AllRBC50100150200250231.22243.61242.12

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: INIVOL and Fluid Structure Interaction Drop ContainerRBC170340510680850773.23774.07740.95

OpenRadioss

Model: Rubber O-Ring Seal Installation

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Rubber O-Ring Seal InstallationRBC50100150200250240.12250.66247.38

OpenRadioss

Model: Cell Phone Drop Test

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Cell Phone Drop TestRBC306090120150123.09118.73118.28

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 4KRBC112233445546.3748.0447.961. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

spaCy

Model: en_core_web_trf

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_trfRBC400800120016002000172017121773

Y-Cruncher

Pi Digits To Calculate: 1B

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 1BRBC112233445549.2647.7947.89

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: CPURBC4812162014.2613.9013.86MIN: 14.16MIN: 13.79MIN: 13.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow

Device: CPU - Batch Size: 16 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: AlexNetRBC2040608010079.9782.2482.26

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPURBC4812162017.7117.3117.24MIN: 17.4MIN: 16.89MIN: 16.891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow

Device: CPU - Batch Size: 32 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: AlexNetRBC306090120150111.34114.35113.81

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: CPURBC2468108.697028.472218.57504MIN: 4.83MIN: 4.83MIN: 4.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow

Device: CPU - Batch Size: 16 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: GoogLeNetRBC142842567062.7964.3463.92

JPEG XL libjxl

Input: JPEG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100RBC0.19130.38260.57390.76520.95650.840.850.831. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

Y-Cruncher

Pi Digits To Calculate: 500M

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 500MRBC51015202522.1121.6021.61

JPEG XL Decoding libjxl

CPU Threads: 1

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: 1RBC142842567060.6561.6462.07

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 1080pRBC306090120150150.57154.03152.961. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 1080pRBC306090120150148.90151.77152.171. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

TensorFlow

Device: CPU - Batch Size: 512 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 512 - Model: AlexNetRBC4080120160200174.50175.41171.68

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: CPURBC369121511.9611.7611.73MIN: 11.87MIN: 11.66MIN: 11.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6RBC2468107.0136.8937.0251. (CXX) g++ options: -O3 -fPIC -lm

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 4KRBC81624324033.7834.3834.401. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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: CPURBC0.28860.57720.86581.15441.4431.260541.282571.28270MIN: 1.22MIN: 1.23MIN: 1.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow

Device: CPU - Batch Size: 256 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: AlexNetRBC4080120160200164.34163.34161.55

QuadRay

Scene: 5 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 5 - Resolution: 1080pRBC0.85281.70562.55843.41124.2643.733.793.771. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

TensorFlow

Device: CPU - Batch Size: 32 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: GoogLeNetRBC153045607564.1165.1264.76

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 1080pRBC306090120150123.87125.54125.611. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

JPEG XL libjxl

Input: PNG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90RBC369121510.3310.4710.401. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

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: CPURBC0.72111.44222.16332.88443.60553.204903.174823.16436MIN: 3.16MIN: 3.11MIN: 3.111. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

JPEG XL libjxl

Input: JPEG - Quality: 80

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 80RBC369121510.1810.3010.291. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

JPEG XL libjxl

Input: PNG - Quality: 100

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 100RBC0.19580.39160.58740.78320.9790.860.870.861. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

JPEG XL libjxl

Input: PNG - Quality: 80

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 80RBC369121510.5310.6510.621. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

TensorFlow

Device: CPU - Batch Size: 64 - Model: AlexNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: AlexNetRBC306090120150135.48137.02136.63

QuadRay

Scene: 5 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 5 - Resolution: 4KRBC0.21380.42760.64140.85521.0690.950.940.941. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

JPEG XL libjxl

Input: JPEG - Quality: 90

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90RBC369121510.0010.1010.081. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic

QuadRay

Scene: 1 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 1 - Resolution: 1080pRBC122436486053.4553.3852.981. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPURBC0.78761.57522.36283.15043.9383.471453.500413.49109MIN: 3.28MIN: 3.28MIN: 3.291. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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-StreamRBC306090120150133.74133.50134.59

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-StreamRBC2468107.46947.48307.4230

TensorFlow

Device: CPU - Batch Size: 512 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 512 - Model: GoogLeNetRBC153045607567.9768.1567.61

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-StreamRBC61218243025.3425.1425.31

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-StreamRBC4080120160200157.73158.99157.96

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-StreamRBC81624324035.2535.4935.52

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-StreamRBC71421283528.3628.1728.15

oneDNN

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPURBC2468108.598368.533468.53868MIN: 8.45MIN: 8.38MIN: 8.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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 4KRBC369121512.0912.1712.131. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

TensorFlow

Device: CPU - Batch Size: 256 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: GoogLeNetRBC153045607567.0266.9066.59

QuadRay

Scene: 2 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 2 - Resolution: 1080pRBC4812162014.1014.0114.061. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: ResNet-50RBC51015202522.1922.3322.20

QuadRay

Scene: 3 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 3 - Resolution: 4KRBC0.72451.4492.17352.8983.62253.203.223.201. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

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 4KRBC2468106.666.706.691. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

TensorFlow

Device: CPU - Batch Size: 64 - Model: GoogLeNet

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: GoogLeNetRBC153045607565.2265.6165.36

spaCy

Model: en_core_web_lg

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_lgRBC3K6K9K12K15K155411561115633

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-StreamRBC4812162014.5714.4914.49

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-StreamRBC153045607568.6069.0069.00

TensorFlow

Device: CPU - Batch Size: 16 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: ResNet-50RBC51015202519.9820.0920.00

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 10, LosslessRBC1.13722.27443.41164.54885.6865.0545.0275.0331. (CXX) g++ options: -O3 -fPIC -lm

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-StreamRBC100200300400500441.46440.47439.15

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-StreamRBC36912159.06059.08109.1082

QuadRay

Scene: 1 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 1 - Resolution: 4KRBC4812162014.1414.2114.171. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 0RBC306090120150144.98144.91145.581. (CXX) g++ options: -O3 -fPIC -lm

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: CPURBC0.18670.37340.56010.74680.93350.8299150.8261200.826113MIN: 0.82MIN: 0.82MIN: 0.811. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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 1080pRBC102030405041.5041.6541.681. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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-StreamRBC90180270360450433.69433.95435.46

OpenRadioss

Model: Bumper Beam

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bumper BeamRBC4080120160200171.69170.99171.23

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-StreamRBC36912159.22299.21739.1853

TensorFlow

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: ResNet-50RBC51015202522.0222.1122.06

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-StreamRBC61218243022.9022.9922.98

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-StreamRBC102030405043.6543.4943.50

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6, LosslessRBC369121510.7010.6610.671. (CXX) g++ options: -O3 -fPIC -lm

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-StreamRBC20406080100111.44111.04111.08

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-StreamRBC36912158.97309.00529.0021

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 1080pRBC4812162016.8716.9316.921. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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-StreamRBC20406080100109.95110.33110.28

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-StreamRBC36912159.09429.06359.0676

TensorFlow

Device: CPU - Batch Size: 32 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: ResNet-50RBC51015202521.3021.3621.32

OpenRadioss

Model: Bird Strike on Windshield

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bird Strike on WindshieldRBC70140210280350308.06307.35308.19

QuadRay

Scene: 2 - Resolution: 4K

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 2 - Resolution: 4KRBC0.84151.6832.52453.3664.20753.743.743.731. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -lpthread

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-StreamRBC91827364541.5741.4941.52

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-StreamRBC2040608010096.2096.4096.34

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-StreamRBC2040608010078.4278.5778.57

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-StreamRBC122436486050.9950.9050.90

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 2RBC153045607568.7368.6268.601. (CXX) g++ options: -O3 -fPIC -lm

QuadRay

Scene: 3 - Resolution: 1080p

OpenBenchmarking.orgFPS, More Is BetterQuadRay 2022.05.25Scene: 3 - Resolution: 1080pRBC369121512.2612.2812.261. (CXX) g++ options: -O3 -pthread -lm -lstdc++ -lX11 -lXext -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-StreamRBC2040608010081.1081.2081.19

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-StreamRBC112233445549.3149.2549.26

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPURBC4812162016.1716.1616.16MIN: 16.08MIN: 16.07MIN: 16.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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-StreamRBC112233445549.8649.8849.91

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-StreamRBC51015202520.0520.0420.03

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPURBC51015202520.1520.1420.14MIN: 19.83MIN: 19.81MIN: 19.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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-StreamRBC81624324036.3836.3836.39

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-StreamRBC20406080100109.92109.93109.90

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 1080pRBC0.15080.30160.45240.60320.7540.670.670.671. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 4KRBC0.04950.0990.14850.1980.24750.220.220.221. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Phoronix Test Suite v10.8.4