m1test

AMD Ryzen 5 7600X 6-Core testing with a ASUS TUF GAMING B650-PLUS WIFI (0823 BIOS) and Gigabyte NVIDIA GeForce RTX 4060 Ti 16GB on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2307293-NE-M1TEST40932
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
firstmachinetest
July 28 2023
  21 Hours, 1 Minute
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


m1testOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 7600X 6-Core @ 4.70GHz (6 Cores / 12 Threads)ASUS TUF GAMING B650-PLUS WIFI (0823 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 2000GBGigabyte NVIDIA GeForce RTX 4060 Ti 16GBNVIDIA Device 22bdDELL P2720DCRealtek RTL8125 2.5GbE + Realtek Device b852Ubuntu 22.045.19.0-50-generic (x86_64)GNOME Shell 42.9X Server 1.21.1.4NVIDIA 535.86.054.6.0OpenCL 3.0 CUDA 12.2.1281.3.224GCC 11.3.0ext42560x1440ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionM1test BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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-aYxV0E/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-aYxV0E/gcc-11-11.3.0/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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203 - BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.06.25.00.ac- GPU Compute Cores: 4352- Python 3.10.6- 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

m1testshoc: OpenCL - Triadshoc: OpenCL - Reductionshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - S3Dshoc: OpenCL - FFT SPshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - MD5 Hashtensorflow: CPU - 16 - VGG-16tensorflow: CPU - 32 - VGG-16tensorflow: CPU - 64 - VGG-16tensorflow: CPU - 16 - AlexNettensorflow: CPU - 256 - VGG-16tensorflow: CPU - 32 - AlexNettensorflow: CPU - 64 - AlexNettensorflow: CPU - 256 - AlexNettensorflow: CPU - 512 - AlexNettensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 32 - GoogLeNettensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 64 - GoogLeNettensorflow: CPU - 64 - ResNet-50tensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNetdeepsparse: 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: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - 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: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - 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 Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamlczero: BLASnumpy: ai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scorespacy: en_core_web_lgspacy: en_core_web_trftensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2onednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUmnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDettnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1opencv: DNN - Deep Neural Networkdeepsparse: 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: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - 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: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - 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 Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepspeech: CPUrnnoise: numenta-nab: KNN CADnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Contextual Anomaly Detector OSEmlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressionscikit-learn: Sparse Rand Projections / 100 Iterationsfirstmachinetest12.9202262.41713.375413.19062697.61167.736726.0466415.7023395.725.92568.458.879.05107.999.09142.72167.60189.83193.9177.3125.6975.5525.5174.5625.2874.3225.1274.518.95038.9435390.9266280.5608167.0395125.594647.421745.0475111.796484.05331259.3116943.253650.010044.69111.24869.5099111.893584.022750.337445.350676.623568.504016.317316.1422184.5994118.661238.596934.84198.94838.95401383807.431809249643051941316571920.4429141.45368.281348.482942.8626415.73.942374.977740.7312671.113401.532282.998078.575215.279415.247388.339241.009451.300842835.961417.352834.983.732038.816653.122001414.692834.581415.385.8940.7591.38811.9202.4771.6892.79716.0407.251.931.481.521.562.690.55.9829.966.284.6911.8713.2110.374.58113.911.8610.703.333.832.543.417.921.059.0768.878.7418.2920.1219.7913.114.46719.183.062181.402182.51241.947177.53012915335.1708111.80717.66093.559917.94657.956163.247822.191426.822911.89102.37531.058159.971322.3672266.6888105.147826.799511.895259.569622.044839.142614.5927183.833661.936416.23718.415977.715628.6962335.2462111.677645.2345213.411169.65112.8339.66792.48918.98830.81727.5033.0914.601.62OpenBenchmarking.org

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: cannot import name 'Iterable' from 'collections' (/usr/lib/python3.10/collections/__init__.py)

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: cannot import name 'Iterable' from 'collections' (/usr/lib/python3.10/collections/__init__.py)

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triadfirstmachinetest3691215SE +/- 0.02, N = 312.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reductionfirstmachinetest60120180240300SE +/- 0.01, N = 3262.421. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Downloadfirstmachinetest3691215SE +/- 0.00, N = 313.381. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readbackfirstmachinetest3691215SE +/- 0.00, N = 313.191. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidthfirstmachinetest6001200180024003000SE +/- 1.89, N = 32697.611. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3Dfirstmachinetest4080120160200SE +/- 0.11, N = 3167.741. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPfirstmachinetest160320480640800SE +/- 0.21, N = 3726.051. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_Nfirstmachinetest14002800420056007000SE +/- 40.91, N = 36415.701. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flopsfirstmachinetest5K10K15K20K25KSE +/- 1.82, N = 323395.71. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hashfirstmachinetest612182430SE +/- 0.00, N = 325.931. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: VGG-16firstmachinetest246810SE +/- 0.01, N = 38.45

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16firstmachinetest246810SE +/- 0.01, N = 38.87

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16firstmachinetest3691215SE +/- 0.00, N = 39.05

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetfirstmachinetest20406080100SE +/- 0.06, N = 3107.99

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: VGG-16firstmachinetest3691215SE +/- 0.00, N = 39.09

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetfirstmachinetest306090120150SE +/- 0.15, N = 3142.72

Device: CPU - Batch Size: 512 - Model: VGG-16

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetfirstmachinetest4080120160200SE +/- 0.18, N = 3167.60

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetfirstmachinetest4080120160200SE +/- 0.06, N = 3189.83

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetfirstmachinetest4080120160200SE +/- 0.03, N = 3193.91

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetfirstmachinetest20406080100SE +/- 0.05, N = 377.31

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50firstmachinetest612182430SE +/- 0.00, N = 325.69

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetfirstmachinetest20406080100SE +/- 0.04, N = 375.55

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50firstmachinetest612182430SE +/- 0.01, N = 325.51

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetfirstmachinetest20406080100SE +/- 0.02, N = 374.56

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50firstmachinetest612182430SE +/- 0.01, N = 325.28

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetfirstmachinetest20406080100SE +/- 0.09, N = 374.32

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50firstmachinetest612182430SE +/- 0.01, N = 325.12

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetfirstmachinetest20406080100SE +/- 0.03, N = 374.51

Device: CPU - Batch Size: 512 - Model: ResNet-50

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

Model: GPT-2 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: GPT-2 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: bertsquad-12 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: bertsquad-12 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: super-resolution-10 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: super-resolution-10 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamfirstmachinetest3691215SE +/- 0.0058, N = 38.9503

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamfirstmachinetest246810SE +/- 0.0065, N = 38.9435

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest80160240320400SE +/- 0.49, N = 3390.93

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest60120180240300SE +/- 0.93, N = 3280.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamfirstmachinetest4080120160200SE +/- 0.17, N = 3167.04

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamfirstmachinetest306090120150SE +/- 0.25, N = 3125.59

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamfirstmachinetest1122334455SE +/- 0.05, N = 347.42

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamfirstmachinetest1020304050SE +/- 0.09, N = 345.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamfirstmachinetest306090120150SE +/- 0.08, N = 3111.80

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamfirstmachinetest20406080100SE +/- 0.16, N = 384.05

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest30060090012001500SE +/- 1.91, N = 31259.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest2004006008001000SE +/- 1.92, N = 3943.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamfirstmachinetest1122334455SE +/- 0.29, N = 350.01

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamfirstmachinetest1020304050SE +/- 0.01, N = 344.69

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamfirstmachinetest3691215SE +/- 0.01, N = 311.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamfirstmachinetest3691215SE +/- 0.0022, N = 39.5099

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamfirstmachinetest306090120150SE +/- 0.03, N = 3111.89

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamfirstmachinetest20406080100SE +/- 0.08, N = 384.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest1122334455SE +/- 0.19, N = 350.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest1020304050SE +/- 0.02, N = 345.35

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamfirstmachinetest20406080100SE +/- 0.07, N = 376.62

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamfirstmachinetest1530456075SE +/- 0.06, N = 368.50

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamfirstmachinetest48121620SE +/- 0.01, N = 316.32

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamfirstmachinetest48121620SE +/- 0.01, N = 316.14

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest4080120160200SE +/- 0.24, N = 3184.60

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest306090120150SE +/- 0.11, N = 3118.66

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamfirstmachinetest918273645SE +/- 0.01, N = 338.60

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamfirstmachinetest816243240SE +/- 0.01, N = 334.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamfirstmachinetest246810SE +/- 0.0017, N = 38.9483

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamfirstmachinetest3691215SE +/- 0.0039, N = 38.9540

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASfirstmachinetest30060090012001500SE +/- 14.53, N = 313831. (CXX) g++ options: -flto -pthread

Numpy Benchmark

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

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkfirstmachinetest2004006008001000SE +/- 0.92, N = 3807.43

AI Benchmark Alpha

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

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Scorefirstmachinetest4008001200160020001809

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Scorefirstmachinetest50010001500200025002496

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Scorefirstmachinetest90018002700360045004305

spaCy

The spaCy library is an open-source solution for advanced neural language processing (NLP). The spaCy library leverages Python and is a leading neural language processing solution. This test profile times the spaCy CPU performance with various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_lgfirstmachinetest4K8K12K16K20KSE +/- 42.55, N = 319413

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_trffirstmachinetest400800120016002000SE +/- 0.33, N = 31657

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetfirstmachinetest400800120016002000SE +/- 1.99, N = 31920.44

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4firstmachinetest6K12K18K24K30KSE +/- 8.55, N = 329141.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilefirstmachinetest12002400360048006000SE +/- 4.80, N = 35368.28

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatfirstmachinetest30060090012001500SE +/- 1.14, N = 31348.48

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantfirstmachinetest6001200180024003000SE +/- 23.86, N = 92942.86

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2firstmachinetest6K12K18K24K30KSE +/- 21.93, N = 326415.7

Caffe

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

Model: AlexNet - Acceleration: CPU - Iterations: 100

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

Model: AlexNet - Acceleration: CPU - Iterations: 200

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

Model: AlexNet - Acceleration: CPU - Iterations: 1000

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

Model: GoogleNet - Acceleration: CPU - Iterations: 100

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

Model: GoogleNet - Acceleration: CPU - Iterations: 200

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

Model: GoogleNet - Acceleration: CPU - Iterations: 1000

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./caffe: 3: ./tools/caffe: not found

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUfirstmachinetest0.8871.7742.6613.5484.435SE +/- 0.00577, N = 33.94237MIN: 3.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUfirstmachinetest1.122.243.364.485.6SE +/- 0.00196, N = 34.97774MIN: 4.891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUfirstmachinetest0.16450.3290.49350.6580.8225SE +/- 0.000672, N = 30.731267MIN: 0.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUfirstmachinetest0.25050.5010.75151.0021.2525SE +/- 0.00745, N = 31.11340MIN: 1.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest0.34480.68961.03441.37921.724SE +/- 0.00143, N = 31.53228MIN: 1.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest0.67461.34922.02382.69843.373SE +/- 0.02962, N = 62.99807MIN: 2.811. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUfirstmachinetest246810SE +/- 0.00397, N = 38.57521MIN: 8.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUfirstmachinetest1.18792.37583.56374.75165.9395SE +/- 0.00118, N = 35.27941MIN: 5.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUfirstmachinetest1.18072.36143.54214.72285.9035SE +/- 0.00166, N = 35.24738MIN: 5.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUfirstmachinetest246810SE +/- 0.04575, N = 38.33924MIN: 8.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUfirstmachinetest0.22710.45420.68130.90841.1355SE +/- 0.00052, N = 31.00945MIN: 0.981. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUfirstmachinetest0.29270.58540.87811.17081.4635SE +/- 0.00296, N = 31.30084MIN: 1.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUfirstmachinetest6001200180024003000SE +/- 1.36, N = 32835.96MIN: 2825.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUfirstmachinetest30060090012001500SE +/- 2.36, N = 31417.35MIN: 1405.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUfirstmachinetest6001200180024003000SE +/- 0.85, N = 32834.98MIN: 2823.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest0.83971.67942.51913.35884.1985SE +/- 0.00482, N = 33.73203MIN: 3.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest246810SE +/- 0.00619, N = 38.81665MIN: 8.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest0.70251.4052.10752.813.5125SE +/- 0.00508, N = 33.12200MIN: 2.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUfirstmachinetest30060090012001500SE +/- 0.08, N = 31414.69MIN: 1406.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest6001200180024003000SE +/- 0.41, N = 32834.58MIN: 2824.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUfirstmachinetest30060090012001500SE +/- 0.23, N = 31415.38MIN: 1406.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetfirstmachinetest1.32622.65243.97865.30486.631SE +/- 0.113, N = 155.894MIN: 5.21 / MAX: 12.961. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3firstmachinetest0.17080.34160.51240.68320.854SE +/- 0.005, N = 150.759MIN: 0.72 / MAX: 8.331. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1firstmachinetest0.31230.62460.93691.24921.5615SE +/- 0.011, N = 151.388MIN: 1.33 / MAX: 10.341. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50firstmachinetest3691215SE +/- 0.06, N = 1511.92MIN: 11.53 / MAX: 38.341. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0firstmachinetest0.55731.11461.67192.22922.7865SE +/- 0.023, N = 152.477MIN: 2.35 / MAX: 10.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224firstmachinetest0.380.761.141.521.9SE +/- 0.012, N = 151.689MIN: 1.59 / MAX: 9.21. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0firstmachinetest0.62931.25861.88792.51723.1465SE +/- 0.002, N = 152.797MIN: 2.76 / MAX: 9.641. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3firstmachinetest48121620SE +/- 0.25, N = 1516.04MIN: 14.1 / MAX: 37.411. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetfirstmachinetest246810SE +/- 0.05, N = 37.25MIN: 7.07 / MAX: 9.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2firstmachinetest0.43430.86861.30291.73722.1715SE +/- 0.00, N = 31.93MIN: 1.87 / MAX: 2.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3firstmachinetest0.3330.6660.9991.3321.665SE +/- 0.00, N = 31.48MIN: 1.46 / MAX: 1.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2firstmachinetest0.3420.6841.0261.3681.71SE +/- 0.00, N = 31.52MIN: 1.48 / MAX: 1.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetfirstmachinetest0.3510.7021.0531.4041.755SE +/- 0.00, N = 31.56MIN: 1.54 / MAX: 1.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0firstmachinetest0.60531.21061.81592.42123.0265SE +/- 0.00, N = 32.69MIN: 2.65 / MAX: 3.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefacefirstmachinetest0.11250.2250.33750.450.5625SE +/- 0.00, N = 30.5MIN: 0.49 / MAX: 0.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetfirstmachinetest1.34552.6914.03655.3826.7275SE +/- 0.02, N = 35.98MIN: 5.87 / MAX: 9.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16firstmachinetest714212835SE +/- 0.01, N = 329.96MIN: 29.64 / MAX: 36.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18firstmachinetest246810SE +/- 0.12, N = 36.28MIN: 6.08 / MAX: 8.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetfirstmachinetest1.05532.11063.16594.22125.2765SE +/- 0.01, N = 34.69MIN: 4.63 / MAX: 7.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50firstmachinetest3691215SE +/- 0.04, N = 311.87MIN: 11.71 / MAX: 14.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyfirstmachinetest3691215SE +/- 0.02, N = 313.21MIN: 12.7 / MAX: 16.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdfirstmachinetest3691215SE +/- 0.01, N = 310.37MIN: 10.14 / MAX: 15.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mfirstmachinetest1.03052.0613.09154.1225.1525SE +/- 0.01, N = 34.58MIN: 4.53 / MAX: 7.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerfirstmachinetest306090120150SE +/- 1.07, N = 3113.91MIN: 112.28 / MAX: 580.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetfirstmachinetest0.41850.8371.25551.6742.0925SE +/- 0.07, N = 31.86MIN: 1.76 / MAX: 4.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetfirstmachinetest3691215SE +/- 0.01, N = 310.70MIN: 9.96 / MAX: 14.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2firstmachinetest0.74931.49862.24792.99723.7465SE +/- 0.00, N = 33.33MIN: 3.25 / MAX: 3.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3firstmachinetest0.86181.72362.58543.44724.309SE +/- 0.01, N = 33.83MIN: 3.72 / MAX: 41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2firstmachinetest0.57151.1431.71452.2862.8575SE +/- 0.07, N = 32.54MIN: 2.39 / MAX: 2.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetfirstmachinetest0.76731.53462.30193.06923.8365SE +/- 0.05, N = 33.41MIN: 3.29 / MAX: 3.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0firstmachinetest246810SE +/- 0.04, N = 37.92MIN: 7.26 / MAX: 8.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefacefirstmachinetest0.23630.47260.70890.94521.1815SE +/- 0.01, N = 31.05MIN: 1.02 / MAX: 1.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetfirstmachinetest3691215SE +/- 0.02, N = 39.07MIN: 8.48 / MAX: 9.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16firstmachinetest1530456075SE +/- 0.02, N = 368.87MIN: 68.54 / MAX: 69.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18firstmachinetest246810SE +/- 0.02, N = 38.74MIN: 8.11 / MAX: 9.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetfirstmachinetest510152025SE +/- 0.01, N = 318.29MIN: 17.98 / MAX: 18.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50firstmachinetest510152025SE +/- 0.01, N = 320.12MIN: 19.86 / MAX: 20.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyfirstmachinetest510152025SE +/- 0.27, N = 319.79MIN: 18.75 / MAX: 25.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdfirstmachinetest3691215SE +/- 0.03, N = 313.11MIN: 12.54 / MAX: 14.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mfirstmachinetest1.00352.0073.01054.0145.0175SE +/- 0.05, N = 34.46MIN: 4.28 / MAX: 4.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerfirstmachinetest160320480640800SE +/- 2.11, N = 3719.18MIN: 692.24 / MAX: 747.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetfirstmachinetest0.68851.3772.06552.7543.4425SE +/- 0.06, N = 33.06MIN: 2.88 / MAX: 3.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetfirstmachinetest5001000150020002500SE +/- 5.49, N = 32181.40MIN: 2152.21 / MAX: 2244.71. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2firstmachinetest4080120160200SE +/- 0.38, N = 3182.51MIN: 179.91 / MAX: 188.171. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2firstmachinetest1020304050SE +/- 0.42, N = 541.95MIN: 40.18 / MAX: 43.011. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1firstmachinetest4080120160200SE +/- 0.09, N = 3177.53MIN: 177.25 / MAX: 177.921. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural Networkfirstmachinetest3K6K9K12K15KSE +/- 66.50, N = 3129151. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamfirstmachinetest70140210280350SE +/- 0.22, N = 3335.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamfirstmachinetest306090120150SE +/- 0.08, N = 3111.81

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest246810SE +/- 0.0094, N = 37.6609

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest0.8011.6022.4033.2044.005SE +/- 0.0117, N = 33.5599

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamfirstmachinetest48121620SE +/- 0.02, N = 317.95

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamfirstmachinetest246810SE +/- 0.0159, N = 37.9561

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamfirstmachinetest1428425670SE +/- 0.06, N = 363.25

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamfirstmachinetest510152025SE +/- 0.04, N = 322.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamfirstmachinetest612182430SE +/- 0.02, N = 326.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamfirstmachinetest3691215SE +/- 0.02, N = 311.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest0.53441.06881.60322.13762.672SE +/- 0.0036, N = 32.3753

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest0.23810.47620.71430.95241.1905SE +/- 0.0021, N = 31.0581

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamfirstmachinetest1326395265SE +/- 0.35, N = 359.97

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamfirstmachinetest510152025SE +/- 0.01, N = 322.37

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamfirstmachinetest60120180240300SE +/- 0.14, N = 3266.69

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamfirstmachinetest20406080100SE +/- 0.02, N = 3105.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamfirstmachinetest612182430SE +/- 0.01, N = 326.80

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamfirstmachinetest3691215SE +/- 0.01, N = 311.90

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest1326395265SE +/- 0.23, N = 359.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest510152025SE +/- 0.01, N = 322.04

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamfirstmachinetest918273645SE +/- 0.04, N = 339.14

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamfirstmachinetest48121620SE +/- 0.01, N = 314.59

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamfirstmachinetest4080120160200SE +/- 0.16, N = 3183.83

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamfirstmachinetest1428425670SE +/- 0.04, N = 361.94

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamfirstmachinetest48121620SE +/- 0.02, N = 316.24

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamfirstmachinetest246810SE +/- 0.0077, N = 38.4159

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamfirstmachinetest20406080100SE +/- 0.02, N = 377.72

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamfirstmachinetest714212835SE +/- 0.01, N = 328.70

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamfirstmachinetest70140210280350SE +/- 0.07, N = 3335.25

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamfirstmachinetest306090120150SE +/- 0.05, N = 3111.68

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUfirstmachinetest1020304050SE +/- 0.03, N = 345.23

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ERROR: Rscript is not found on the system!

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28firstmachinetest3691215SE +/- 0.04, N = 313.411. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

Benchmark: P1B2

firstmachinetest: The test quit with a non-zero exit status. E: ValueError: decay is deprecated in the new Keras optimizer, please check the docstring for valid arguments, or use the legacy optimizer, e.g., tf.keras.optimizers.legacy.RMSprop.

Benchmark: P3B1

firstmachinetest: The test quit with a non-zero exit status. E: ValueError: decay is deprecated in the new Keras optimizer, please check the docstring for valid arguments, or use the legacy optimizer, e.g., tf.keras.optimizers.legacy.SGD.

Benchmark: P3B2

firstmachinetest: The test quit with a non-zero exit status. E: AttributeError: module 'numpy' has no attribute 'bool'.

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADfirstmachinetest4080120160200SE +/- 1.13, N = 3169.65

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropyfirstmachinetest3691215SE +/- 0.12, N = 1512.83

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussianfirstmachinetest3691215SE +/- 0.092, N = 159.667

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinefirstmachinetest20406080100SE +/- 0.55, N = 392.49

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointfirstmachinetest510152025SE +/- 0.17, N = 1518.99

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEfirstmachinetest714212835SE +/- 0.18, N = 330.82

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icafirstmachinetest612182430SE +/- 0.07, N = 327.50

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdafirstmachinetest816243240SE +/- 0.13, N = 333.09

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmfirstmachinetest48121620SE +/- 0.00, N = 314.60

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionfirstmachinetest0.36450.7291.09351.4581.8225SE +/- 0.01, N = 31.62

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: GLM

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SAGA

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Tree

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Lasso

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Glmnet

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sparsify

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Ward

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: MNIST Dataset

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Neighbors

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SGD Regression

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SGDOneClassSVM

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Lasso Path

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isolation Forest

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Fast KMeans

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Text Vectorizers

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Hierarchical

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot OMP vs. LARS

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Feature Expansions

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: LocalOutlierFactor

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: TSNE MNIST Dataset

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Logistic

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Incremental PCA

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Parallel Pairwise

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Pathological

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: RCV1 Logreg Convergencet

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sample Without Replacement

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Covertype Dataset Benchmark

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Adult

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Perturbed Logarithm

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Threading

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Singular Value Decomposition

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/libblas.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Higgs Boson

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: 20 Newsgroups / Logistic Regression

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Polynomial Kernel Approximation

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Non-Negative Matrix Factorization

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Categorical Only

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Kernel PCA Solvers / Time vs. N Samples

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Kernel PCA Solvers / Time vs. N Components

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sparse Random Projections / 100 Iterations

firstmachinetest: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

181 Results Shown

SHOC Scalable HeterOgeneous Computing:
  OpenCL - Triad
  OpenCL - Reduction
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
  OpenCL - S3D
  OpenCL - FFT SP
  OpenCL - GEMM SGEMM_N
  OpenCL - Max SP Flops
  OpenCL - MD5 Hash
TensorFlow:
  CPU - 16 - VGG-16
  CPU - 32 - VGG-16
  CPU - 64 - VGG-16
  CPU - 16 - AlexNet
  CPU - 256 - VGG-16
  CPU - 32 - AlexNet
  CPU - 64 - AlexNet
  CPU - 256 - AlexNet
  CPU - 512 - AlexNet
  CPU - 16 - GoogLeNet
  CPU - 16 - ResNet-50
  CPU - 32 - GoogLeNet
  CPU - 32 - ResNet-50
  CPU - 64 - GoogLeNet
  CPU - 64 - ResNet-50
  CPU - 256 - GoogLeNet
  CPU - 256 - ResNet-50
  CPU - 512 - GoogLeNet
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  ResNet-50, Baseline - Synchronous Single-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Synchronous Single-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Synchronous Single-Stream
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
LeelaChessZero
Numpy Benchmark
AI Benchmark Alpha:
  Device Inference Score
  Device Training Score
  Device AI Score
spaCy:
  en_core_web_lg
  en_core_web_trf
TensorFlow Lite:
  SqueezeNet
  Inception V4
  NASNet Mobile
  Mobilenet Float
  Mobilenet Quant
  Inception ResNet V2
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 1D - bf16bf16bf16 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Mobile Neural Network:
  nasnet
  mobilenetV3
  squeezenetv1.1
  resnet-v2-50
  SqueezeNetV1.0
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - regnety_400m
  Vulkan GPU - vision_transformer
  Vulkan GPU - FastestDet
TNN:
  CPU - DenseNet
  CPU - MobileNet v2
  CPU - SqueezeNet v2
  CPU - SqueezeNet v1.1
OpenCV
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  ResNet-50, Baseline - Synchronous Single-Stream
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Synchronous Single-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Synchronous Single-Stream
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
DeepSpeech
RNNoise
Numenta Anomaly Benchmark:
  KNN CAD
  Relative Entropy
  Windowed Gaussian
  Earthgecko Skyline
  Bayesian Changepoint
  Contextual Anomaly Detector OSE
Mlpack Benchmark:
  scikit_ica
  scikit_qda
  scikit_svm
  scikit_linearridgeregression