ML

Intel Core i7-12700H testing with a Intel NUC12SNKi72 (SNADL357.0055.2022.0923.1555 BIOS) and Intel Arctm A770M DG2 16GB on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2305318-NE-ML327025586
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 Arctm A770M DG2
May 30 2023
  2 Days, 50 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):


MLOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-12700H @ 4.60GHz (14 Cores / 20 Threads)Intel NUC12SNKi72 (SNADL357.0055.2022.0923.1555 BIOS)Intel Alder Lake PCH16GB1024GB SAMSUNG MZVL21T0HCLR-00A00Intel Arctm A770M DG2 16GB (1400MHz)Realtek ALC274S27H85xIntel I225-LM + Intel Alder Lake-P PCH CNVi WiFiUbuntu 22.045.19.0-42-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.3 + Wayland4.6 Mesa 23.1.0-devel (git-722bcd7973)OpenCL 3.0 + OpenCL 3.01.3.238GCC 11.3.0ext42560x1440ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionML BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-aYxV0E/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-aYxV0E/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x429 - Thermald 2.4.9 - Python 3.10.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

MLshoc: OpenCL - S3Dshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Reductionshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthlczero: BLASonednn: 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 - CPUnumpy: deepspeech: CPUrbenchmark: rnnoise: tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2tensorflow: 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 - GoogLeNettensorflow: CPU - 512 - GoogLeNetdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamspacy: en_core_web_lgspacy: en_core_web_trfcaffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200caffe: AlexNet - CPU - 1000caffe: GoogleNet - CPU - 100caffe: GoogleNet - CPU - 200caffe: GoogleNet - CPU - 1000mnn: 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: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUnumenta-nab: KNN CADnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Contextual Anomaly Detector OSEai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scoremlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressionopencv: DNN - Deep Neural NetworkIntel Arctm A770M DG274.682811.00361253.7018.261275.0282186.71143958611.757711.33691124.0211323.9480311.30101.406592.4802515.86739.120107.6427715.62021.892823.213144363.752199.964377.602190.974387.132198.98568.4165.914830.105714.7732642.6837029.6114426.01916.033248.53129929.45.365.535.5476.22100.35118.53144.49154.0855.0916.2754.9116.7556.8216.9958.4359.457.7657895.02687.3377136.277894.932173.650161.069416.367729.2966238.116022.497744.441348.1926144.969439.523625.2934104.145767.153170.128314.254966.0015105.861852.113019.185110.1681684.00379.6843103.246332.7644212.588926.112238.29267.7507897.71167.3345136.337216538123233092674493417949304518708694048210.9271.5083.70328.0365.8233.1813.81730.91111.853.272.792.943.155.771.149.3240.448.666.6915.5718.3712.469.41203.134.0821.285.497.713.644.9817.101.5920.5916.7917.543.2222.5324.4421.1510.441487.8920.431992.465191.61443.227149.2272.512364.501.573708.471.563747.64174.8634.248.96662.97463.3912.90264.4857.4928.49210.29929.6221.50371.6816.108722.192.299443.092.11189.83814.0408.10791.99422.23033.23410891631272039.7148.4412.542.0933936OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DIntel Arctm A770M DG220406080100SE +/- 0.03, N = 374.681. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadIntel Arctm A770M DG23691215SE +/- 0.00, N = 311.001. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPIntel Arctm A770M DG230060090012001500SE +/- 0.50, N = 31253.701. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashIntel Arctm A770M DG248121620SE +/- 0.03, N = 318.261. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionIntel Arctm A770M DG260120180240300SE +/- 0.23, N = 3275.031. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NIntel Arctm A770M DG25001000150020002500SE +/- 19.21, N = 82186.711. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsIntel Arctm A770M DG2300K600K900K1200K1500KSE +/- 72882.34, N = 1314395861. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadIntel Arctm A770M DG23691215SE +/- 0.00, N = 311.761. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackIntel Arctm A770M DG23691215SE +/- 0.00, N = 311.341. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthIntel Arctm A770M DG22004006008001000SE +/- 3.54, N = 31124.021. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

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 Arctm A770M DG22004006008001000SE +/- 13.39, N = 411321. (CXX) g++ options: -flto -pthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUIntel Arctm A770M DG20.88831.77662.66493.55324.4415SE +/- 0.00177, N = 33.94803MIN: 3.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUIntel Arctm A770M DG23691215SE +/- 0.00, N = 311.30MIN: 11.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG20.31650.6330.94951.2661.5825SE +/- 0.00916, N = 31.40659MIN: 1.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG20.55811.11621.67432.23242.7905SE +/- 0.00815, N = 32.48025MIN: 2.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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

Intel Arctm A770M DG2: 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 Arctm A770M DG2: 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 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUIntel Arctm A770M DG248121620SE +/- 0.01, N = 315.87MIN: 15.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUIntel Arctm A770M DG23691215SE +/- 0.01542, N = 39.12010MIN: 4.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUIntel Arctm A770M DG2246810SE +/- 0.01110, N = 37.64277MIN: 7.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG248121620SE +/- 0.01, N = 315.62MIN: 15.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG20.42590.85181.27771.70362.1295SE +/- 0.00073, N = 31.89282MIN: 1.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG20.7231.4462.1692.8923.615SE +/- 0.00195, N = 33.21314MIN: 3.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUIntel Arctm A770M DG29001800270036004500SE +/- 32.87, N = 34363.75MIN: 4268.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUIntel Arctm A770M DG25001000150020002500SE +/- 2.50, N = 32199.96MIN: 2149.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG29001800270036004500SE +/- 2.77, N = 34377.60MIN: 4272.061. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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

Intel Arctm A770M DG2: 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 Arctm A770M DG2: 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 Arctm A770M DG2: 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 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUIntel Arctm A770M DG25001000150020002500SE +/- 8.39, N = 32190.97MIN: 2149.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUIntel Arctm A770M DG29001800270036004500SE +/- 13.68, N = 34387.13MIN: 4265.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUIntel Arctm A770M DG25001000150020002500SE +/- 2.31, N = 32198.98MIN: 2149.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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 Arctm A770M DG2120240360480600SE +/- 1.10, N = 3568.41

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 Arctm A770M DG21530456075SE +/- 0.11, N = 365.91

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 Arctm A770M DG20.02380.04760.07140.09520.119SE +/- 0.0010, N = 150.10571. R scripting front-end version 4.1.2 (2021-11-01)

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 Arctm A770M DG248121620SE +/- 0.03, N = 314.771. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

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 Arctm A770M DG26001200180024003000SE +/- 24.06, N = 72642.68

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4Intel Arctm A770M DG28K16K24K32K40KSE +/- 250.09, N = 337029.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileIntel Arctm A770M DG220K40K60K80K100KSE +/- 5238.95, N = 12114426.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatIntel Arctm A770M DG2400800120016002000SE +/- 22.41, N = 41916.03

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantIntel Arctm A770M DG27001400210028003500SE +/- 34.95, N = 53248.53

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Intel Arctm A770M DG230K60K90K120K150KSE +/- 13225.33, N = 15129929.4

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 Arctm A770M DG21.2062.4123.6184.8246.03SE +/- 0.01, N = 35.36

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16Intel Arctm A770M DG21.24432.48863.73294.97726.2215SE +/- 0.01, N = 35.53

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16Intel Arctm A770M DG21.24652.4933.73954.9866.2325SE +/- 0.04, N = 35.54

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetIntel Arctm A770M DG220406080100SE +/- 0.09, N = 376.22

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetIntel Arctm A770M DG220406080100SE +/- 0.03, N = 3100.35

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

Intel Arctm A770M DG2: 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: Segmentation fault

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetIntel Arctm A770M DG2306090120150SE +/- 0.07, N = 3118.53

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetIntel Arctm A770M DG2306090120150SE +/- 0.16, N = 3144.49

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetIntel Arctm A770M DG2306090120150SE +/- 0.28, N = 3154.08

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetIntel Arctm A770M DG21224364860SE +/- 0.05, N = 355.09

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Intel Arctm A770M DG248121620SE +/- 0.00, N = 316.27

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetIntel Arctm A770M DG21224364860SE +/- 0.05, N = 354.91

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50Intel Arctm A770M DG248121620SE +/- 0.00, N = 316.75

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetIntel Arctm A770M DG21326395265SE +/- 0.13, N = 356.82

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50Intel Arctm A770M DG248121620SE +/- 0.01, N = 316.99

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetIntel Arctm A770M DG21326395265SE +/- 0.05, N = 358.43

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetIntel Arctm A770M DG21326395265SE +/- 0.02, N = 359.45

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

Intel Arctm A770M DG2: 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: Segmentation fault

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2246810SE +/- 0.0110, N = 37.7657

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG22004006008001000SE +/- 1.39, N = 3895.03

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2246810SE +/- 0.0059, N = 37.3377

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2306090120150SE +/- 0.11, N = 3136.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG220406080100SE +/- 0.50, N = 394.93

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG21632486480SE +/- 0.39, N = 373.65

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-StreamIntel Arctm A770M DG21428425670SE +/- 0.33, N = 361.07

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-StreamIntel Arctm A770M DG248121620SE +/- 0.09, N = 316.37

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2714212835SE +/- 0.17, N = 329.30

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG250100150200250SE +/- 1.34, N = 3238.12

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2510152025SE +/- 0.07, N = 322.50

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG21020304050SE +/- 0.15, N = 344.44

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG21122334455SE +/- 0.26, N = 348.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2306090120150SE +/- 0.80, N = 3144.97

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2918273645SE +/- 0.10, N = 339.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2612182430SE +/- 0.06, N = 325.29

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG220406080100SE +/- 0.38, N = 3104.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG21530456075SE +/- 0.27, N = 367.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel Arctm A770M DG21632486480SE +/- 0.31, N = 370.13

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel Arctm A770M DG248121620SE +/- 0.06, N = 314.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG21530456075SE +/- 0.40, N = 366.00

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG220406080100SE +/- 0.62, N = 3105.86

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel Arctm A770M DG21224364860SE +/- 0.13, N = 352.11

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2510152025SE +/- 0.05, N = 319.19

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG23691215SE +/- 0.05, N = 310.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2150300450600750SE +/- 4.26, N = 3684.00

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel Arctm A770M DG23691215SE +/- 0.0145, N = 39.6843

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel Arctm A770M DG220406080100SE +/- 0.15, N = 3103.25

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2816243240SE +/- 0.09, N = 332.76

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG250100150200250SE +/- 0.61, N = 3212.59

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2612182430SE +/- 0.06, N = 326.11

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2918273645SE +/- 0.09, N = 338.29

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG2246810SE +/- 0.0141, N = 37.7507

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel Arctm A770M DG22004006008001000SE +/- 1.03, N = 3897.71

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2246810SE +/- 0.0106, N = 37.3345

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel Arctm A770M DG2306090120150SE +/- 0.20, N = 3136.34

spaCy

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

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_lgIntel Arctm A770M DG24K8K12K16K20KSE +/- 15.06, N = 316538

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_trfIntel Arctm A770M DG230060090012001500SE +/- 2.91, N = 31232

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 Arctm A770M DG27K14K21K28K35KSE +/- 153.54, N = 3330921. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200Intel Arctm A770M DG214K28K42K56K70KSE +/- 236.68, N = 3674491. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 1000Intel Arctm A770M DG270K140K210K280K350KSE +/- 950.21, N = 33417941. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100Intel Arctm A770M DG220K40K60K80K100KSE +/- 268.60, N = 3930451. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200Intel Arctm A770M DG240K80K120K160K200KSE +/- 638.93, N = 31870861. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 1000Intel Arctm A770M DG2200K400K600K800K1000KSE +/- 1731.20, N = 39404821. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 Arctm A770M DG23691215SE +/- 0.10, N = 1210.93MIN: 9.86 / MAX: 47.61. (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 Arctm A770M DG20.33930.67861.01791.35721.6965SE +/- 0.046, N = 121.508MIN: 1.3 / MAX: 8.131. (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 Arctm A770M DG20.83321.66642.49963.33284.166SE +/- 0.142, N = 123.703MIN: 2.82 / MAX: 43.091. (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 Arctm A770M DG2714212835SE +/- 0.98, N = 1228.04MIN: 23.35 / MAX: 56.651. (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 Arctm A770M DG21.31022.62043.93065.24086.551SE +/- 0.112, N = 125.823MIN: 4.91 / MAX: 40.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224Intel Arctm A770M DG20.71571.43142.14712.86283.5785SE +/- 0.033, N = 123.181MIN: 2.57 / MAX: 12.011. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0Intel Arctm A770M DG20.85881.71762.57643.43524.294SE +/- 0.252, N = 123.817MIN: 3.14 / MAX: 28.691. (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 Arctm A770M DG2714212835SE +/- 0.62, N = 1230.91MIN: 28.06 / MAX: 69.931. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetIntel Arctm A770M DG23691215SE +/- 0.28, N = 1211.85MIN: 10.3 / MAX: 20.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2Intel Arctm A770M DG20.73581.47162.20742.94323.679SE +/- 0.07, N = 123.27MIN: 2.95 / MAX: 5.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3Intel Arctm A770M DG20.62781.25561.88342.51123.139SE +/- 0.05, N = 122.79MIN: 2.48 / MAX: 7.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2Intel Arctm A770M DG20.66151.3231.98452.6463.3075SE +/- 0.06, N = 122.94MIN: 2.71 / MAX: 8.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetIntel Arctm A770M DG20.70881.41762.12642.83523.544SE +/- 0.10, N = 123.15MIN: 2.58 / MAX: 8.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0Intel Arctm A770M DG21.29832.59663.89495.19326.4915SE +/- 0.10, N = 125.77MIN: 5.12 / MAX: 15.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceIntel Arctm A770M DG20.25650.5130.76951.0261.2825SE +/- 0.02, N = 121.14MIN: 0.96 / MAX: 3.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetIntel Arctm A770M DG23691215SE +/- 0.07, N = 129.32MIN: 8.79 / MAX: 17.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16Intel Arctm A770M DG2918273645SE +/- 0.42, N = 1240.44MIN: 37.76 / MAX: 424.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18Intel Arctm A770M DG2246810SE +/- 0.07, N = 128.66MIN: 8.44 / MAX: 153.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetIntel Arctm A770M DG2246810SE +/- 0.02, N = 126.69MIN: 6.49 / MAX: 11.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50Intel Arctm A770M DG248121620SE +/- 0.05, N = 1215.57MIN: 15.14 / MAX: 24.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyIntel Arctm A770M DG2510152025SE +/- 0.24, N = 1218.37MIN: 17.29 / MAX: 327.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdIntel Arctm A770M DG23691215SE +/- 0.08, N = 1212.46MIN: 11.96 / MAX: 20.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mIntel Arctm A770M DG23691215SE +/- 0.24, N = 129.41MIN: 8.33 / MAX: 16.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerIntel Arctm A770M DG24080120160200SE +/- 1.74, N = 12203.13MIN: 181.8 / MAX: 966.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetIntel Arctm A770M DG20.9181.8362.7543.6724.59SE +/- 0.20, N = 124.08MIN: 3.32 / MAX: 27.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetIntel Arctm A770M DG2510152025SE +/- 0.60, N = 921.28MIN: 15.6 / MAX: 68.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Intel Arctm A770M DG21.23532.47063.70594.94126.1765SE +/- 1.25, N = 95.49MIN: 3.29 / MAX: 38.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Intel Arctm A770M DG2246810SE +/- 1.71, N = 97.71MIN: 3.54 / MAX: 35.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2Intel Arctm A770M DG20.8191.6382.4573.2764.095SE +/- 0.25, N = 93.64MIN: 2.93 / MAX: 22.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetIntel Arctm A770M DG21.12052.2413.36154.4825.6025SE +/- 0.70, N = 94.98MIN: 3.4 / MAX: 39.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0Intel Arctm A770M DG248121620SE +/- 1.05, N = 917.10MIN: 7.31 / MAX: 38.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceIntel Arctm A770M DG20.35780.71561.07341.43121.789SE +/- 0.10, N = 91.59MIN: 1.31 / MAX: 5.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetIntel Arctm A770M DG2510152025SE +/- 0.30, N = 920.59MIN: 9.29 / MAX: 40.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16Intel Arctm A770M DG248121620SE +/- 0.32, N = 916.79MIN: 14.77 / MAX: 45.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18Intel Arctm A770M DG248121620SE +/- 0.51, N = 917.54MIN: 6.07 / MAX: 37.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetIntel Arctm A770M DG20.72451.4492.17352.8983.6225SE +/- 0.68, N = 93.22MIN: 2.08 / MAX: 35.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50Intel Arctm A770M DG2510152025SE +/- 0.39, N = 822.53MIN: 10.36 / MAX: 39.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyIntel Arctm A770M DG2612182430SE +/- 0.71, N = 924.44MIN: 20.18 / MAX: 81.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdIntel Arctm A770M DG2510152025SE +/- 0.37, N = 921.15MIN: 12.63 / MAX: 83.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mIntel Arctm A770M DG23691215SE +/- 1.98, N = 910.44MIN: 4.82 / MAX: 36.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerIntel Arctm A770M DG230060090012001500SE +/- 4.49, N = 91487.89MIN: 695.27 / MAX: 2143.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetIntel Arctm A770M DG2510152025SE +/- 1.11, N = 920.43MIN: 4.71 / MAX: 37.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetIntel Arctm A770M DG2400800120016002000SE +/- 1.57, N = 31992.47MIN: 1913.75 / MAX: 2125.391. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Intel Arctm A770M DG24080120160200SE +/- 0.39, N = 3191.61MIN: 184.04 / MAX: 217.571. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Intel Arctm A770M DG21020304050SE +/- 0.03, N = 343.23MIN: 42.91 / MAX: 43.661. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Intel Arctm A770M DG2306090120150SE +/- 0.10, N = 3149.23MIN: 148.73 / MAX: 150.291. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

PlaidML

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

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: cannot import name 'Iterable' from 'collections' (/usr/lib/python3.10/collections/__init__.py)

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: cannot import name 'Iterable' from 'collections' (/usr/lib/python3.10/collections/__init__.py)

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 2022.3Model: Face Detection FP16 - Device: CPUIntel Arctm A770M DG20.56481.12961.69442.25922.824SE +/- 0.03, N = 42.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUIntel Arctm A770M DG25001000150020002500SE +/- 17.33, N = 42364.50MIN: 1171.79 / MAX: 2888.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUIntel Arctm A770M DG20.35330.70661.05991.41321.7665SE +/- 0.01, N = 31.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUIntel Arctm A770M DG28001600240032004000SE +/- 27.05, N = 33708.47MIN: 2911.35 / MAX: 4667.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUIntel Arctm A770M DG20.3510.7021.0531.4041.755SE +/- 0.02, N = 31.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUIntel Arctm A770M DG28001600240032004000SE +/- 46.22, N = 33747.64MIN: 3027.95 / MAX: 4624.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUIntel Arctm A770M DG24080120160200SE +/- 0.43, N = 3174.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUIntel Arctm A770M DG2816243240SE +/- 0.09, N = 334.24MIN: 13 / MAX: 46.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG23691215SE +/- 0.08, N = 38.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG2140280420560700SE +/- 5.52, N = 3662.97MIN: 284.46 / MAX: 1378.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG2100200300400500SE +/- 4.89, N = 3463.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG23691215SE +/- 0.14, N = 312.90MIN: 7.03 / MAX: 28.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUIntel Arctm A770M DG260120180240300SE +/- 3.36, N = 3264.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUIntel Arctm A770M DG21326395265SE +/- 17.14, N = 357.49MIN: 17.08 / MAX: 102.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUIntel Arctm A770M DG2714212835SE +/- 0.16, N = 328.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUIntel Arctm A770M DG250100150200250SE +/- 1.20, N = 3210.29MIN: 165.03 / MAX: 293.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG22004006008001000SE +/- 13.36, N = 3929.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUIntel Arctm A770M DG2510152025SE +/- 0.30, N = 321.50MIN: 9.43 / MAX: 54.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUIntel Arctm A770M DG280160240320400SE +/- 2.76, N = 11371.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUIntel Arctm A770M DG248121620SE +/- 0.12, N = 1116.10MIN: 8.47 / MAX: 29.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel Arctm A770M DG22K4K6K8K10KSE +/- 98.26, N = 48722.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel Arctm A770M DG20.51531.03061.54592.06122.5765SE +/- 0.03, N = 42.29MIN: 1.01 / MAX: 14.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel Arctm A770M DG22K4K6K8K10KSE +/- 101.33, N = 59443.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel Arctm A770M DG20.47480.94961.42441.89922.374SE +/- 0.02, N = 52.11MIN: 0.98 / MAX: 13.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 Arctm A770M DG2: The test quit with a non-zero exit status. E: ValueError: decay is deprecated in the new Keras optimizer, pleasecheck the docstring for valid arguments, or use the legacy optimizer, e.g., tf.keras.optimizers.legacy.RMSprop.

Benchmark: P3B1

Intel Arctm A770M DG2: The test quit with a non-zero exit status. E: ValueError: decay is deprecated in the new Keras optimizer, pleasecheck the docstring for valid arguments, or use the legacy optimizer, e.g., tf.keras.optimizers.legacy.SGD.

Benchmark: P3B2

Intel Arctm A770M DG2: The test quit with a non-zero exit status. E: ValueError: decay is deprecated in the new Keras optimizer, pleasecheck the docstring for valid arguments, or use the legacy optimizer, e.g., tf.keras.optimizers.legacy.RMSprop.

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 Arctm A770M DG24080120160200SE +/- 1.52, N = 3189.84

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyIntel Arctm A770M DG248121620SE +/- 0.15, N = 314.04

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianIntel Arctm A770M DG2246810SE +/- 0.113, N = 38.107

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineIntel Arctm A770M DG220406080100SE +/- 0.95, N = 1591.99

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointIntel Arctm A770M DG2510152025SE +/- 0.34, N = 1522.23

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEIntel Arctm A770M DG2816243240SE +/- 0.12, N = 333.23

ONNX Runtime

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

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Parallel

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

Model: yolov4 - Device: CPU - Executor: Standard

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

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

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./onnx: line 2: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

AI Benchmark Alpha

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

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreIntel Arctm A770M DG220040060080010001089

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreIntel Arctm A770M DG24008001200160020001631

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreIntel Arctm A770M DG260012001800240030002720

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 Arctm A770M DG2918273645SE +/- 0.05, N = 339.71

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaIntel Arctm A770M DG21122334455SE +/- 0.65, N = 1548.44

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmIntel Arctm A770M DG23691215SE +/- 0.03, N = 312.54

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionIntel Arctm A770M DG20.47030.94061.41091.88122.3515SE +/- 0.02, N = 42.09

Scikit-Learn

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

Benchmark: GLM

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SAGA

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Tree

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Lasso

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Glmnet

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sparsify

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Ward

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: MNIST Dataset

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Neighbors

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SGD Regression

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: SGDOneClassSVM

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Lasso Path

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isolation Forest

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Fast KMeans

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Text Vectorizers

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Hierarchical

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot OMP vs. LARS

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Feature Expansions

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: LocalOutlierFactor

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: TSNE MNIST Dataset

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Logistic

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Incremental PCA

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Parallel Pairwise

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Pathological

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: RCV1 Logreg Convergencet

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sample Without Replacement

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Covertype Dataset Benchmark

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Adult

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Isotonic / Perturbed Logarithm

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Threading

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Singular Value Decomposition

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/libblas.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Higgs Boson

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: 20 Newsgroups / Logistic Regression

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Polynomial Kernel Approximation

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Plot Non-Negative Matrix Factorization

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Hist Gradient Boosting Categorical Only

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Kernel PCA Solvers / Time vs. N Samples

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Kernel PCA Solvers / Time vs. N Components

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

Benchmark: Sparse Random Projections / 100 Iterations

Intel Arctm A770M DG2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ImportError: /lib/x86_64-linux-gnu/liblapack.so.3: undefined symbol: gotoblas

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 Arctm A770M DG27K14K21K28K35KSE +/- 1700.61, N = 15339361. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

181 Results Shown

SHOC Scalable HeterOgeneous Computing:
  OpenCL - S3D
  OpenCL - Triad
  OpenCL - FFT SP
  OpenCL - MD5 Hash
  OpenCL - Reduction
  OpenCL - GEMM SGEMM_N
  OpenCL - Max SP Flops
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
LeelaChessZero
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
Numpy Benchmark
DeepSpeech
R Benchmark
RNNoise
TensorFlow Lite:
  SqueezeNet
  Inception V4
  NASNet Mobile
  Mobilenet Float
  Mobilenet Quant
  Inception ResNet V2
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
  CPU - 512 - GoogLeNet
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch
spaCy:
  en_core_web_lg
  en_core_web_trf
Caffe:
  AlexNet - CPU - 100
  AlexNet - CPU - 200
  AlexNet - CPU - 1000
  GoogleNet - CPU - 100
  GoogleNet - CPU - 200
  GoogleNet - CPU - 1000
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:
    FPS
    ms
  Person Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP32 - CPU:
    FPS
    ms
  Vehicle Detection FP16 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
Numenta Anomaly Benchmark:
  KNN CAD
  Relative Entropy
  Windowed Gaussian
  Earthgecko Skyline
  Bayesian Changepoint
  Contextual Anomaly Detector OSE
AI Benchmark Alpha:
  Device Inference Score
  Device Training Score
  Device AI Score
Mlpack Benchmark:
  scikit_ica
  scikit_qda
  scikit_svm
  scikit_linearridgeregression
OpenCV