h510-i310100-1

Intel Core i3-10100 testing with a ASRock H510M-HVS (P1.60 BIOS) and Intel UHD 630 CML GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2312018-HERT-H510I3137
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
Intel UHD 630 CML GT2
November 21 2023
  3 Days, 14 Hours, 21 Minutes
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):


h510-i310100-1OpenBenchmarking.orgPhoronix Test SuiteIntel Core i3-10100 @ 4.30GHz (4 Cores / 8 Threads)ASRock H510M-HVS (P1.60 BIOS)Intel Device 43ef3584MB1000GB Western Digital WDS100T2B0AIntel UHD 630 CML GT2 3GB (1100MHz)Realtek ALC897G185BGEL01Realtek RTL8111/8168/8411Ubuntu 20.045.15.0-88-generic (x86_64)GNOME Shell 3.36.9X Server 1.20.134.6 Mesa 21.2.61.2.182GCC 9.4.0ext41368x768ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionH510-i310100-1 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf8 - Thermald 1.9.1 - Python 3.8.10- gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

h510-i310100-1pytorch: CPU - 1 - ResNet-50pytorch: CPU - 1 - ResNet-152pytorch: CPU - 16 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 16 - ResNet-152pytorch: CPU - 256 - ResNet-50pytorch: CPU - 32 - ResNet-152pytorch: CPU - 512 - ResNet-50pytorch: CPU - 64 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 512 - ResNet-152pytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_lplaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - ResNet 50 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUtensorflow: CPU - 16 - VGG-16tensorflow: CPU - 32 - VGG-16tensorflow: CPU - 64 - VGG-16tensorflow: CPU - 16 - AlexNettensorflow: 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 - GoogLeNetonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standarddeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: 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 Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamlczero: BLASnumpy: onnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardtensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2caffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200caffe: AlexNet - CPU - 1000caffe: GoogleNet - CPU - 100caffe: GoogleNet - CPU - 200caffe: GoogleNet - CPU - 1000onednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - 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: 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 v1.1openvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopencv: 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: 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 Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepspeech: CPUrbenchmark: rnnoise: numenta-nab: KNN CADnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Contextual Anomaly Detector OSEmlpack: scikit_icamlpack: scikit_svmscikit-learn: GLMscikit-learn: SAGAscikit-learn: Treescikit-learn: Lassoscikit-learn: Sparsifyscikit-learn: Plot Wardscikit-learn: MNIST Datasetscikit-learn: Plot Neighborsscikit-learn: SGD Regressionscikit-learn: Plot Lasso Pathscikit-learn: Text Vectorizersscikit-learn: Plot Hierarchicalscikit-learn: Plot OMP vs. LARSscikit-learn: Feature Expansionsscikit-learn: LocalOutlierFactorscikit-learn: TSNE MNIST Datasetscikit-learn: Plot Incremental PCAscikit-learn: Hist Gradient Boostingscikit-learn: Sample Without Replacementscikit-learn: Covertype Dataset Benchmarkscikit-learn: Hist Gradient Boosting Adultscikit-learn: Hist Gradient Boosting Threadingscikit-learn: Plot Singular Value Decompositionscikit-learn: Hist Gradient Boosting Higgs Bosonscikit-learn: 20 Newsgroups / Logistic Regressionscikit-learn: Plot Polynomial Kernel Approximationscikit-learn: Hist Gradient Boosting Categorical Onlyscikit-learn: Kernel PCA Solvers / Time vs. N Samplesscikit-learn: Kernel PCA Solvers / Time vs. N Componentsscikit-learn: Sparse Rand Projections / 100 Iterationswhisper-cpp: ggml-base.en - 2016 State of the Unionwhisper-cpp: ggml-small.en - 2016 State of the Unionwhisper-cpp: ggml-medium.en - 2016 State of the UnionIntel UHD 630 CML GT212.825.996.956.937.073.417.133.427.133.503.443.404.432.212.272.272.252.276.093.371.097.967.9643.492.18138.0410.30101.81102.52387.4338.6910.24215.0685.8939.301937.8547.694197.731.851.581.0521.6528.1232.8936.8036.8311.173.8411.452.9511.501.744.8444.842147.64513.913785.24740139.501158.5880.4144430.5744779.8947114.113959.745775.885128.330242.69723.189973.965082.95992.897867.130864.010243.809638.5862245.3409222.301718.841318.64994.16844.170441.868939.782719.305718.861727.561024.10873.94793.704332.085531.41842.92702.8786147326.4722.295720.9917255.551190.6167.167966.304392437.661740.74101.06570.857816.738213.177635.375923.4197313.481252.1997050.2698713.217768.75753.916821.9288427.765490131136662266154104309367154636712.781832.19263.101555.5006159.666710.437715.062652.10494.349297.8871410295.86656.3810313.96632.5410350.76626.1415.1012.1414.13249.7509.3645.7685.89157.66040.4710.906.533.176.7513.840.9726.08148.3922.0918.0851.4659.4726.0210.28168.976.0640.4510.906.553.186.7713.910.9926.11148.8322.0418.1251.5159.6025.9710.31169.326.024010.894346.03770.172313.9653660.46502.35502.3291.921829.8028.95388.2239.2738.9910.31103.35390.3118.5846.56101.722.0483.840.9440614675.6880345.080829.765115.614145.631725.93388.12954.4891106.136753.6062479.2767239.752147.735325.1270103.565253.011472.546041.4709506.5650269.941462.308131.8181683.2662347.3802106.126960.267525.322401.28639.53218.367395.734126.12999.64584.7325.551042.3441013.79445.329560.618100.83282.99482.151174.833152.300357.73074.609256.952191.998195.642127.759467.52954.071158.501137.887556.13294.914361.508330.978170.73862.132275.14123.303430.917355.1861736.464419.510491335.206344481.6887OpenBenchmarking.org

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50Intel UHD 630 CML GT23691215SE +/- 0.14, N = 312.82MIN: 11.44 / MAX: 13.27

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152Intel UHD 630 CML GT21.34782.69564.04345.39126.739SE +/- 0.05, N = 105.99MIN: 4.82 / MAX: 6.56

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50Intel UHD 630 CML GT2246810SE +/- 0.05, N = 36.95MIN: 5.81 / MAX: 7.09

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50Intel UHD 630 CML GT2246810SE +/- 0.03, N = 36.93MIN: 6.1 / MAX: 7.05

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Intel UHD 630 CML GT2246810SE +/- 0.03, N = 37.07MIN: 5.87 / MAX: 7.19

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152Intel UHD 630 CML GT20.76731.53462.30193.06923.8365SE +/- 0.03, N = 83.41MIN: 2.68 / MAX: 3.64

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Intel UHD 630 CML GT2246810SE +/- 0.03, N = 37.13MIN: 5.96 / MAX: 7.25

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152Intel UHD 630 CML GT20.76951.5392.30853.0783.8475SE +/- 0.04, N = 43.42MIN: 2.62 / MAX: 3.57

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50Intel UHD 630 CML GT2246810SE +/- 0.03, N = 37.13MIN: 6.8 / MAX: 7.27

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152Intel UHD 630 CML GT20.78751.5752.36253.153.9375SE +/- 0.01, N = 33.50MIN: 3.08 / MAX: 3.55

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152Intel UHD 630 CML GT20.7741.5482.3223.0963.87SE +/- 0.01, N = 33.44MIN: 3.25 / MAX: 3.54

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152Intel UHD 630 CML GT20.7651.532.2953.063.825SE +/- 0.01, N = 33.40MIN: 3.22 / MAX: 3.54

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.99681.99362.99043.98724.984SE +/- 0.04, N = 34.43MIN: 3.87 / MAX: 4.55

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.49730.99461.49191.98922.4865SE +/- 0.01, N = 32.21MIN: 1.47 / MAX: 2.26

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.51081.02161.53242.04322.554SE +/- 0.00, N = 32.27MIN: 1.95 / MAX: 2.32

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.51081.02161.53242.04322.554SE +/- 0.00, N = 32.27MIN: 2.11 / MAX: 2.32

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.50631.01261.51892.02522.5315SE +/- 0.01, N = 32.25MIN: 2.07 / MAX: 2.3

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lIntel UHD 630 CML GT20.51081.02161.53242.04322.554SE +/- 0.01, N = 32.27MIN: 2.1 / MAX: 2.3

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.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUIntel UHD 630 CML GT2246810SE +/- 0.08, N = 96.09

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUIntel UHD 630 CML GT20.75831.51662.27493.03323.7915SE +/- 0.01, N = 33.37

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUIntel UHD 630 CML GT20.24530.49060.73590.98121.2265SE +/- 0.01, N = 31.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUIntel UHD 630 CML GT2246810SE +/- 0.02, N = 37.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUIntel UHD 630 CML GT2246810SE +/- 0.00, N = 37.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUIntel UHD 630 CML GT21020304050SE +/- 0.06, N = 343.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT20.49050.9811.47151.9622.4525SE +/- 0.02, N = 32.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUIntel UHD 630 CML GT2306090120150SE +/- 0.83, N = 3138.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUIntel UHD 630 CML GT23691215SE +/- 0.02, N = 310.301. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 1.23, N = 4101.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 0.45, N = 3102.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUIntel UHD 630 CML GT280160240320400SE +/- 1.31, N = 3387.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUIntel UHD 630 CML GT2918273645SE +/- 0.30, N = 338.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUIntel UHD 630 CML GT23691215SE +/- 0.08, N = 310.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT250100150200250SE +/- 2.50, N = 3215.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 1.16, N = 385.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUIntel UHD 630 CML GT2918273645SE +/- 0.20, N = 339.301. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel UHD 630 CML GT2400800120016002000SE +/- 5.88, N = 31937.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUIntel UHD 630 CML GT21122334455SE +/- 0.31, N = 347.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel UHD 630 CML GT29001800270036004500SE +/- 34.38, N = 34197.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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-16Intel UHD 630 CML GT20.41630.83261.24891.66522.0815SE +/- 0.02, N = 91.85

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16Intel UHD 630 CML GT20.35550.7111.06651.4221.7775SE +/- 0.02, N = 41.58

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16Intel UHD 630 CML GT20.23630.47260.70890.94521.1815SE +/- 0.01, N = 31.05

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetIntel UHD 630 CML GT2510152025SE +/- 0.01, N = 321.65

Device: CPU - Batch Size: 256 - Model: VGG-16

Intel UHD 630 CML GT2: 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: Fatal Python error: Aborted

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetIntel UHD 630 CML GT2714212835SE +/- 0.01, N = 328.12

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

Intel UHD 630 CML GT2: 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: Fatal Python error: Aborted

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetIntel UHD 630 CML GT2816243240SE +/- 0.04, N = 332.89

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetIntel UHD 630 CML GT2816243240SE +/- 0.05, N = 336.80

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetIntel UHD 630 CML GT2816243240SE +/- 0.19, N = 336.83

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetIntel UHD 630 CML GT23691215SE +/- 0.00, N = 311.17

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Intel UHD 630 CML GT20.8641.7282.5923.4564.32SE +/- 0.00, N = 33.84

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetIntel UHD 630 CML GT23691215SE +/- 0.00, N = 311.45

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50Intel UHD 630 CML GT20.66381.32761.99142.65523.319SE +/- 0.07, N = 92.95

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetIntel UHD 630 CML GT23691215SE +/- 0.01, N = 311.50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50Intel UHD 630 CML GT20.39150.7831.17451.5661.9575SE +/- 0.05, N = 31.74

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetIntel UHD 630 CML GT21.0892.1783.2674.3565.445SE +/- 0.06, N = 34.84

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

Intel UHD 630 CML GT2: 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.

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

Intel UHD 630 CML GT2: 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.

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

Intel UHD 630 CML GT2: 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.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT21020304050SE +/- 0.02, N = 344.841. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardIntel UHD 630 CML GT21122334455SE +/- 0.64, N = 347.651. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

Model: yolov4 - Device: CPU - Executor: Parallel

Intel UHD 630 CML GT2: 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: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory

Model: yolov4 - Device: CPU - Executor: Standard

Intel UHD 630 CML GT2: 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: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT20.88061.76122.64183.52244.403SE +/- 0.03748, N = 33.913781. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardIntel UHD 630 CML GT21.18072.36143.54214.72285.9035SE +/- 0.05913, N = 35.247401. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT2306090120150SE +/- 1.19, N = 3139.501. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardIntel UHD 630 CML GT24080120160200SE +/- 0.33, N = 3158.591. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT20.09320.18640.27960.37280.466SE +/- 0.013144, N = 120.4144431. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardIntel UHD 630 CML GT20.12930.25860.38790.51720.6465SE +/- 0.001607, N = 30.5744771. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT23691215SE +/- 0.03496, N = 39.894711. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardIntel UHD 630 CML GT248121620SE +/- 0.10, N = 314.111. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT21326395265SE +/- 0.48, N = 359.751. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardIntel UHD 630 CML GT220406080100SE +/- 0.51, N = 375.891. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT2714212835SE +/- 0.35, N = 1528.331. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardIntel UHD 630 CML GT21020304050SE +/- 0.21, N = 342.701. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelIntel UHD 630 CML GT20.71771.43542.15312.87083.5885SE +/- 0.00431, N = 33.189971. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardIntel UHD 630 CML GT20.89211.78422.67633.56844.4605SE +/- 0.00587, N = 33.965081. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT20.6661.3321.9982.6643.33SE +/- 0.0082, N = 32.9599

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT20.6521.3041.9562.6083.26SE +/- 0.0089, N = 32.8978

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21530456075SE +/- 0.20, N = 367.13

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT21428425670SE +/- 0.03, N = 364.01

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/sentiment_analysis/bert-base/pytorch/huggingface/sst2/12layer_pruned90-none.Please try another stub

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/sentiment_analysis/bert-base/pytorch/huggingface/sst2/12layer_pruned90-none.Please try another stub

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

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/question_answering/bert-base/pytorch/huggingface/squad/12layer_pruned90-none.Please try another stub

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

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/question_answering/bert-base/pytorch/huggingface/squad/12layer_pruned90-none.Please try another stub

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21020304050SE +/- 0.02, N = 343.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2918273645SE +/- 0.33, N = 1538.59

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT250100150200250SE +/- 0.20, N = 3245.34

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT250100150200250SE +/- 0.42, N = 3222.30

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2510152025SE +/- 0.15, N = 318.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2510152025SE +/- 0.03, N = 318.65

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT20.93791.87582.81373.75164.6895SE +/- 0.0105, N = 34.1684

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT20.93831.87662.81493.75324.6915SE +/- 0.0148, N = 34.1704

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21020304050SE +/- 0.43, N = 341.87

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2918273645SE +/- 0.01, N = 339.78

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2510152025SE +/- 0.05, N = 319.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2510152025SE +/- 0.12, N = 318.86

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2612182430SE +/- 0.02, N = 327.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2612182430SE +/- 0.03, N = 324.11

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT20.88831.77662.66493.55324.4415SE +/- 0.0071, N = 33.9479

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT20.83351.6672.50053.3344.1675SE +/- 0.0016, N = 33.7043

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2714212835SE +/- 0.13, N = 332.09

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2714212835SE +/- 0.03, N = 331.42

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

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/text_classification/bert-base/pytorch/huggingface/sst2/base-none.Please try another stub

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

Intel UHD 630 CML GT2: 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: ValueError: No matching models found with stub: nlp/text_classification/bert-base/pytorch/huggingface/sst2/base-none.Please try another stub

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT20.65861.31721.97582.63443.293SE +/- 0.0047, N = 32.9270

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT20.64771.29541.94312.59083.2385SE +/- 0.0025, N = 32.8786

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: BLASIntel UHD 630 CML GT2306090120150SE +/- 0.88, N = 31471. (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 BenchmarkIntel UHD 630 CML GT270140210280350SE +/- 0.64, N = 3326.47

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.

Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: AttributeError: module 'numpy' has no attribute 'typeDict'

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.

Intel UHD 630 CML GT2: 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: TypeError: issubclass() arg 1 must be a class

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: SqueezeNetIntel UHD 630 CML GT215003000450060007500SE +/- 76.69, N = 37050.26

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4Intel UHD 630 CML GT220K40K60K80K100KSE +/- 603.06, N = 398713.2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileIntel UHD 630 CML GT24K8K12K16K20KSE +/- 77.55, N = 317768.7

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatIntel UHD 630 CML GT212002400360048006000SE +/- 51.68, N = 35753.91

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantIntel UHD 630 CML GT215003000450060007500SE +/- 34.47, N = 36821.92

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Intel UHD 630 CML GT220K40K60K80K100KSE +/- 773.95, N = 388427.7

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.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100Intel UHD 630 CML GT214K28K42K56K70KSE +/- 3.33, N = 3654901. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200Intel UHD 630 CML GT230K60K90K120K150KSE +/- 323.65, N = 31311361. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 1000Intel UHD 630 CML GT2140K280K420K560K700KSE +/- 715.63, N = 36622661. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100Intel UHD 630 CML GT230K60K90K120K150KSE +/- 66.36, N = 31541041. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200Intel UHD 630 CML GT270K140K210K280K350KSE +/- 632.99, N = 33093671. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 1000Intel UHD 630 CML GT2300K600K900K1200K1500KSE +/- 1702.77, N = 315463671. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT23691215SE +/- 0.03, N = 312.78MIN: 12.361. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT2714212835SE +/- 0.10, N = 332.19MIN: 31.631. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT20.69781.39562.09342.79123.489SE +/- 0.00765, N = 33.10155MIN: 3.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT21.23762.47523.71284.95046.188SE +/- 0.02096, N = 35.50061MIN: 5.141. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT21326395265SE +/- 0.02, N = 359.67MIN: 59.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT23691215SE +/- 0.18, N = 1310.44MIN: 9.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT248121620SE +/- 0.10, N = 315.06MIN: 14.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT21224364860SE +/- 0.03, N = 352.10MIN: 51.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT20.97861.95722.93583.91444.893SE +/- 0.01766, N = 34.34929MIN: 4.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT2246810SE +/- 0.07881, N = 57.88714MIN: 7.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT22K4K6K8K10KSE +/- 31.02, N = 310295.8MIN: 10197.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUIntel UHD 630 CML GT214002800420056007000SE +/- 15.81, N = 36656.38MIN: 6584.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT22K4K6K8K10KSE +/- 12.15, N = 310313.9MIN: 10251.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUIntel UHD 630 CML GT214002800420056007000SE +/- 31.44, N = 36632.54MIN: 6538.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUIntel UHD 630 CML GT22K4K6K8K10KSE +/- 29.88, N = 310350.7MIN: 10265.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUIntel UHD 630 CML GT214002800420056007000SE +/- 39.36, N = 36626.14MIN: 65141. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -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: nasnetIntel UHD 630 CML GT248121620SE +/- 0.12, N = 315.10MIN: 13.64 / MAX: 29.771. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3Intel UHD 630 CML GT20.48170.96341.44511.92682.4085SE +/- 0.024, N = 32.141MIN: 2.04 / MAX: 9.881. (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: squeezenetv1.1Intel UHD 630 CML GT20.92971.85942.78913.71884.6485SE +/- 0.035, N = 34.132MIN: 4.01 / MAX: 6.941. (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-v2-50Intel UHD 630 CML GT21122334455SE +/- 0.11, N = 349.75MIN: 49.05 / MAX: 64.841. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0Intel UHD 630 CML GT23691215SE +/- 0.061, N = 39.364MIN: 9.14 / MAX: 23.051. (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_224Intel UHD 630 CML GT21.29782.59563.89345.19126.489SE +/- 0.045, N = 35.768MIN: 5.61 / MAX: 20.211. (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-v1-1.0Intel UHD 630 CML GT21.32552.6513.97655.3026.6275SE +/- 0.046, N = 35.891MIN: 5.66 / MAX: 19.271. (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-v3Intel UHD 630 CML GT21326395265SE +/- 0.28, N = 357.66MIN: 56.01 / MAX: 109.591. (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 20230517Target: CPU - Model: mobilenetIntel UHD 630 CML GT2918273645SE +/- 0.09, N = 340.47MIN: 40.08 / MAX: 83.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2Intel UHD 630 CML GT23691215SE +/- 0.06, N = 310.90MIN: 10.69 / MAX: 21.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3Intel UHD 630 CML GT2246810SE +/- 0.03, N = 36.53MIN: 6.38 / MAX: 8.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2Intel UHD 630 CML GT20.71331.42662.13992.85323.5665SE +/- 0.01, N = 33.17MIN: 3.11 / MAX: 3.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetIntel UHD 630 CML GT2246810SE +/- 0.03, N = 36.75MIN: 6.55 / MAX: 7.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0Intel UHD 630 CML GT248121620SE +/- 0.07, N = 313.84MIN: 13.52 / MAX: 16.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceIntel UHD 630 CML GT20.21830.43660.65490.87321.0915SE +/- 0.01, N = 30.97MIN: 0.92 / MAX: 1.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetIntel UHD 630 CML GT2612182430SE +/- 0.13, N = 326.08MIN: 25.8 / MAX: 37.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16Intel UHD 630 CML GT2306090120150SE +/- 0.17, N = 3148.39MIN: 147.62 / MAX: 159.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18Intel UHD 630 CML GT2510152025SE +/- 0.03, N = 322.09MIN: 21.88 / MAX: 24.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetIntel UHD 630 CML GT248121620SE +/- 0.01, N = 318.08MIN: 17.91 / MAX: 19.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50Intel UHD 630 CML GT21224364860SE +/- 0.03, N = 351.46MIN: 51.1 / MAX: 62.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyIntel UHD 630 CML GT21326395265SE +/- 0.06, N = 359.47MIN: 59.15 / MAX: 62.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdIntel UHD 630 CML GT2612182430SE +/- 0.06, N = 326.02MIN: 25.58 / MAX: 30.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mIntel UHD 630 CML GT23691215SE +/- 0.01, N = 310.28MIN: 10.19 / MAX: 12.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerIntel UHD 630 CML GT24080120160200SE +/- 0.79, N = 3168.97MIN: 166.92 / MAX: 2911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetIntel UHD 630 CML GT2246810SE +/- 0.06, N = 36.06MIN: 5.87 / MAX: 15.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetIntel UHD 630 CML GT2918273645SE +/- 0.10, N = 340.45MIN: 40.09 / MAX: 42.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Intel UHD 630 CML GT23691215SE +/- 0.02, N = 310.90MIN: 10.73 / MAX: 12.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Intel UHD 630 CML GT2246810SE +/- 0.03, N = 36.55MIN: 6.4 / MAX: 8.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2Intel UHD 630 CML GT20.71551.4312.14652.8623.5775SE +/- 0.00, N = 33.18MIN: 3.13 / MAX: 4.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetIntel UHD 630 CML GT2246810SE +/- 0.02, N = 36.77MIN: 6.6 / MAX: 7.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0Intel UHD 630 CML GT248121620SE +/- 0.04, N = 313.91MIN: 13.62 / MAX: 24.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceIntel UHD 630 CML GT20.22280.44560.66840.89121.114SE +/- 0.01, N = 30.99MIN: 0.94 / MAX: 1.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetIntel UHD 630 CML GT2612182430SE +/- 0.04, N = 326.11MIN: 25.89 / MAX: 29.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16Intel UHD 630 CML GT2306090120150SE +/- 0.09, N = 3148.83MIN: 147.68 / MAX: 188.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18Intel UHD 630 CML GT2510152025SE +/- 0.05, N = 322.04MIN: 21.78 / MAX: 33.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetIntel UHD 630 CML GT248121620SE +/- 0.01, N = 318.12MIN: 17.95 / MAX: 27.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50Intel UHD 630 CML GT21224364860SE +/- 0.08, N = 351.51MIN: 50.97 / MAX: 62.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyIntel UHD 630 CML GT21326395265SE +/- 0.04, N = 359.60MIN: 59.31 / MAX: 69.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdIntel UHD 630 CML GT2612182430SE +/- 0.06, N = 325.97MIN: 25.51 / MAX: 26.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mIntel UHD 630 CML GT23691215SE +/- 0.02, N = 310.31MIN: 10.21 / MAX: 12.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerIntel UHD 630 CML GT24080120160200SE +/- 1.11, N = 3169.32MIN: 167 / MAX: 180.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetIntel UHD 630 CML GT2246810SE +/- 0.03, N = 36.02MIN: 5.87 / MAX: 17.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

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: DenseNetIntel UHD 630 CML GT29001800270036004500SE +/- 9.20, N = 34010.89MIN: 3963.22 / MAX: 4047.461. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Intel UHD 630 CML GT280160240320400SE +/- 0.51, N = 3346.04MIN: 343.36 / MAX: 348.141. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Intel UHD 630 CML GT21632486480SE +/- 0.56, N = 370.17MIN: 68.98 / MAX: 71.711. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Intel UHD 630 CML GT270140210280350SE +/- 0.62, N = 3313.97MIN: 312.4 / MAX: 317.351. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUIntel UHD 630 CML GT28001600240032004000SE +/- 36.52, N = 33660.46MIN: 3432.69 / MAX: 4026.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUIntel UHD 630 CML GT2110220330440550SE +/- 1.06, N = 3502.35MIN: 452.28 / MAX: 549.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUIntel UHD 630 CML GT2110220330440550SE +/- 0.10, N = 3502.32MIN: 458.24 / MAX: 574.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 0.12, N = 391.92MIN: 26.91 / MAX: 143.91. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT2400800120016002000SE +/- 17.01, N = 31829.80MIN: 1646.16 / MAX: 1966.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUIntel UHD 630 CML GT2714212835SE +/- 0.18, N = 328.95MIN: 10.02 / MAX: 74.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUIntel UHD 630 CML GT280160240320400SE +/- 0.76, N = 3388.22MIN: 194.63 / MAX: 454.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT2918273645SE +/- 0.47, N = 439.27MIN: 16.66 / MAX: 66.51. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUIntel UHD 630 CML GT2918273645SE +/- 0.18, N = 338.99MIN: 21.94 / MAX: 59.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUIntel UHD 630 CML GT23691215SE +/- 0.03, N = 310.31MIN: 6 / MAX: 27.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 0.79, N = 3103.35MIN: 47.57 / MAX: 127.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUIntel UHD 630 CML GT280160240320400SE +/- 2.90, N = 3390.31MIN: 182.4 / MAX: 427.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUIntel UHD 630 CML GT2510152025SE +/- 0.22, N = 318.58MIN: 9.94 / MAX: 31.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUIntel UHD 630 CML GT21122334455SE +/- 0.64, N = 346.56MIN: 25.67 / MAX: 86.31. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 0.51, N = 3101.72MIN: 54.27 / MAX: 134.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel UHD 630 CML GT20.4590.9181.3771.8362.295SE +/- 0.01, N = 32.04MIN: 1.03 / MAX: 27.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUIntel UHD 630 CML GT220406080100SE +/- 0.53, N = 383.84MIN: 71.98 / MAX: 109.31. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel UHD 630 CML GT20.21150.4230.63450.8461.0575SE +/- 0.01, N = 30.94MIN: 0.49 / MAX: 23.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -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 NetworkIntel UHD 630 CML GT29K18K27K36K45KSE +/- 453.54, N = 15406141. (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-StreamIntel UHD 630 CML GT2150300450600750SE +/- 1.89, N = 3675.69

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT270140210280350SE +/- 1.06, N = 3345.08

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2714212835SE +/- 0.08, N = 329.77

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT248121620SE +/- 0.01, N = 315.61

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21020304050SE +/- 0.02, N = 345.63

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2612182430SE +/- 0.23, N = 1525.93

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2246810SE +/- 0.0070, N = 38.1295

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT21.012.023.034.045.05SE +/- 0.0085, N = 34.4891

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT220406080100SE +/- 0.85, N = 3106.14

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT21224364860SE +/- 0.07, N = 353.61

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2100200300400500SE +/- 1.38, N = 3479.28

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT250100150200250SE +/- 0.87, N = 3239.75

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21122334455SE +/- 0.49, N = 347.74

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2612182430SE +/- 0.01, N = 325.13

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT220406080100SE +/- 0.30, N = 3103.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT21224364860SE +/- 0.35, N = 353.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21632486480SE +/- 0.05, N = 372.55

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2918273645SE +/- 0.05, N = 341.47

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2110220330440550SE +/- 0.91, N = 3506.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT260120180240300SE +/- 0.11, N = 3269.94

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT21428425670SE +/- 0.25, N = 362.31

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT2714212835SE +/- 0.03, N = 331.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel UHD 630 CML GT2150300450600750SE +/- 1.08, N = 3683.27

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel UHD 630 CML GT280160240320400SE +/- 0.31, N = 3347.38

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: CPUIntel UHD 630 CML GT220406080100SE +/- 0.17, N = 3106.13

R Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkIntel UHD 630 CML GT20.06020.12040.18060.24080.301SE +/- 0.0005, N = 30.26751. R scripting front-end version 3.6.3 (2020-02-29)

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 2020-06-28Intel UHD 630 CML GT2612182430SE +/- 0.06, N = 325.321. (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

Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed

Benchmark: P3B1

Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed

Benchmark: P3B2

Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed

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 CADIntel UHD 630 CML GT290180270360450SE +/- 5.44, N = 3401.29

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyIntel UHD 630 CML GT2918273645SE +/- 0.41, N = 539.53

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianIntel UHD 630 CML GT2510152025SE +/- 0.08, N = 318.37

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineIntel UHD 630 CML GT290180270360450SE +/- 1.84, N = 3395.73

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointIntel UHD 630 CML GT2306090120150SE +/- 1.45, N = 3126.13

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEIntel UHD 630 CML GT220406080100SE +/- 0.25, N = 399.65

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaIntel UHD 630 CML GT220406080100SE +/- 0.83, N = 384.73

Benchmark: scikit_qda

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmIntel UHD 630 CML GT2612182430SE +/- 0.07, N = 325.55

Benchmark: scikit_linearridgeregression

Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: GLMIntel UHD 630 CML GT22004006008001000SE +/- 5.27, N = 31042.341. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SAGAIntel UHD 630 CML GT22004006008001000SE +/- 1.13, N = 31013.791. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TreeIntel UHD 630 CML GT21020304050SE +/- 0.47, N = 1545.331. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: LassoIntel UHD 630 CML GT2120240360480600SE +/- 0.60, N = 3560.621. (F9X) gfortran options: -O0

Benchmark: Glmnet

Intel UHD 630 CML GT2: 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: ModuleNotFoundError: No module named 'glmnet.elastic_net'

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SparsifyIntel UHD 630 CML GT220406080100SE +/- 0.10, N = 3100.831. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot WardIntel UHD 630 CML GT220406080100SE +/- 0.13, N = 382.991. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: MNIST DatasetIntel UHD 630 CML GT220406080100SE +/- 0.06, N = 382.151. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot NeighborsIntel UHD 630 CML GT24080120160200SE +/- 1.47, N = 12174.831. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGD RegressionIntel UHD 630 CML GT2306090120150SE +/- 1.35, N = 3152.301. (F9X) gfortran options: -O0

Benchmark: SGDOneClassSVM

Intel UHD 630 CML GT2: 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.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Lasso PathIntel UHD 630 CML GT280160240320400SE +/- 0.82, N = 3357.731. (F9X) gfortran options: -O0

Benchmark: Isolation Forest

Intel UHD 630 CML GT2: 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.

Benchmark: Plot Fast KMeans

Intel UHD 630 CML GT2: 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.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Text VectorizersIntel UHD 630 CML GT220406080100SE +/- 0.04, N = 374.611. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot HierarchicalIntel UHD 630 CML GT260120180240300SE +/- 0.29, N = 3256.951. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot OMP vs. LARSIntel UHD 630 CML GT24080120160200SE +/- 0.03, N = 3192.001. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Feature ExpansionsIntel UHD 630 CML GT24080120160200SE +/- 0.21, N = 3195.641. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: LocalOutlierFactorIntel UHD 630 CML GT2306090120150SE +/- 0.81, N = 3127.761. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TSNE MNIST DatasetIntel UHD 630 CML GT2100200300400500SE +/- 0.75, N = 3467.531. (F9X) gfortran options: -O0

Benchmark: Isotonic / Logistic

Intel UHD 630 CML GT2: 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.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Incremental PCAIntel UHD 630 CML GT21224364860SE +/- 0.23, N = 354.071. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient BoostingIntel UHD 630 CML GT24080120160200SE +/- 0.13, N = 3158.501. (F9X) gfortran options: -O0

Benchmark: Plot Parallel Pairwise

Intel UHD 630 CML GT2: 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: numpy.core._exceptions.MemoryError: Unable to allocate 74.5 GiB for an array with shape (100000, 100000) and data type float64

Benchmark: Isotonic / Pathological

Intel UHD 630 CML GT2: 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.

Benchmark: RCV1 Logreg Convergencet

Intel UHD 630 CML GT2: 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: IndexError: list index out of range

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sample Without ReplacementIntel UHD 630 CML GT2306090120150SE +/- 1.51, N = 3137.891. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Covertype Dataset BenchmarkIntel UHD 630 CML GT2120240360480600SE +/- 0.59, N = 3556.131. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting AdultIntel UHD 630 CML GT220406080100SE +/- 0.28, N = 394.911. (F9X) gfortran options: -O0

Benchmark: Isotonic / Perturbed Logarithm

Intel UHD 630 CML GT2: 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.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting ThreadingIntel UHD 630 CML GT280160240320400SE +/- 3.09, N = 3361.511. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Singular Value DecompositionIntel UHD 630 CML GT270140210280350SE +/- 2.13, N = 3330.981. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Higgs BosonIntel UHD 630 CML GT24080120160200SE +/- 21.85, N = 12170.741. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: 20 Newsgroups / Logistic RegressionIntel UHD 630 CML GT21428425670SE +/- 0.54, N = 862.131. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Polynomial Kernel ApproximationIntel UHD 630 CML GT260120180240300SE +/- 0.84, N = 3275.141. (F9X) gfortran options: -O0

Benchmark: Plot Non-Negative Matrix Factorization

Intel UHD 630 CML GT2: 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: KeyError:

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Categorical OnlyIntel UHD 630 CML GT2612182430SE +/- 0.05, N = 323.301. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N SamplesIntel UHD 630 CML GT290180270360450SE +/- 0.55, N = 3430.921. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N ComponentsIntel UHD 630 CML GT280160240320400SE +/- 5.16, N = 9355.191. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sparse Random Projections / 100 IterationsIntel UHD 630 CML GT2400800120016002000SE +/- 18.11, N = 51736.461. (F9X) gfortran options: -O0

Whisper.cpp

Whisper.cpp is a port of OpenAI's Whisper model in C/C++. Whisper.cpp is developed by Georgi Gerganov for transcribing WAV audio files to text / speech recognition. Whisper.cpp supports ARM NEON, x86 AVX, and other advanced CPU features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-base.en - Input: 2016 State of the UnionIntel UHD 630 CML GT290180270360450SE +/- 0.30, N = 3419.511. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-small.en - Input: 2016 State of the UnionIntel UHD 630 CML GT230060090012001500SE +/- 1.20, N = 31335.211. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-medium.en - Input: 2016 State of the UnionIntel UHD 630 CML GT210002000300040005000SE +/- 15.31, N = 34481.691. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

256 Results Shown

PyTorch:
  CPU - 1 - ResNet-50
  CPU - 1 - ResNet-152
  CPU - 16 - ResNet-50
  CPU - 32 - ResNet-50
  CPU - 64 - ResNet-50
  CPU - 16 - ResNet-152
  CPU - 256 - ResNet-50
  CPU - 32 - ResNet-152
  CPU - 512 - ResNet-50
  CPU - 64 - ResNet-152
  CPU - 256 - ResNet-152
  CPU - 512 - ResNet-152
  CPU - 1 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
  CPU - 32 - Efficientnet_v2_l
  CPU - 64 - Efficientnet_v2_l
  CPU - 256 - Efficientnet_v2_l
  CPU - 512 - Efficientnet_v2_l
PlaidML:
  No - Inference - VGG16 - CPU
  No - Inference - ResNet 50 - CPU
OpenVINO:
  Face Detection FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
  Vehicle Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
TensorFlow:
  CPU - 16 - VGG-16
  CPU - 32 - VGG-16
  CPU - 64 - VGG-16
  CPU - 16 - AlexNet
  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
ONNX Runtime:
  GPT-2 - CPU - Parallel
  GPT-2 - CPU - Standard
  bertsquad-12 - CPU - Parallel
  bertsquad-12 - CPU - Standard
  CaffeNet 12-int8 - CPU - Parallel
  CaffeNet 12-int8 - CPU - Standard
  fcn-resnet101-11 - CPU - Parallel
  fcn-resnet101-11 - CPU - Standard
  ArcFace ResNet-100 - CPU - Parallel
  ArcFace ResNet-100 - CPU - Standard
  ResNet50 v1-12-int8 - CPU - Parallel
  ResNet50 v1-12-int8 - CPU - Standard
  super-resolution-10 - CPU - Parallel
  super-resolution-10 - CPU - Standard
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel
  Faster R-CNN R-50-FPN-int8 - CPU - Standard
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
  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 Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
LeelaChessZero
Numpy Benchmark
TensorFlow Lite:
  SqueezeNet
  Inception V4
  NASNet Mobile
  Mobilenet Float
  Mobilenet Quant
  Inception ResNet V2
Caffe:
  AlexNet - CPU - 100
  AlexNet - CPU - 200
  AlexNet - CPU - 1000
  GoogleNet - CPU - 100
  GoogleNet - CPU - 200
  GoogleNet - CPU - 1000
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - 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
  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
OpenVINO:
  Face Detection FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
  Vehicle Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
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
  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 Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream
DeepSpeech
R Benchmark
RNNoise
Numenta Anomaly Benchmark:
  KNN CAD
  Relative Entropy
  Windowed Gaussian
  Earthgecko Skyline
  Bayesian Changepoint
  Contextual Anomaly Detector OSE
Mlpack Benchmark:
  scikit_ica
  scikit_svm
Scikit-Learn:
  GLM
  SAGA
  Tree
  Lasso
  Sparsify
  Plot Ward
  MNIST Dataset
  Plot Neighbors
  SGD Regression
  Plot Lasso Path
  Text Vectorizers
  Plot Hierarchical
  Plot OMP vs. LARS
  Feature Expansions
  LocalOutlierFactor
  TSNE MNIST Dataset
  Plot Incremental PCA
  Hist Gradient Boosting
  Sample Without Replacement
  Covertype Dataset Benchmark
  Hist Gradient Boosting Adult
  Hist Gradient Boosting Threading
  Plot Singular Value Decomposition
  Hist Gradient Boosting Higgs Boson
  20 Newsgroups / Logistic Regression
  Plot Polynomial Kernel Approximation
  Hist Gradient Boosting Categorical Only
  Kernel PCA Solvers / Time vs. N Samples
  Kernel PCA Solvers / Time vs. N Components
  Sparse Rand Projections / 100 Iterations
Whisper.cpp:
  ggml-base.en - 2016 State of the Union
  ggml-small.en - 2016 State of the Union
  ggml-medium.en - 2016 State of the Union