H610-i312100-1

Intel Core i3-12100 testing with a ASRock H610M-HDV/M.2 R2.0 (6.03 BIOS) and Intel ADL-S GT1 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 2408228-HERT-H610I3171
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 ADL-S GT1 - Intel Core i3-12100
August 20
  2 Days, 17 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):

Intel ADL-S GT1 - Intel Core i3-12100

Processor: Intel Core i3-12100 @ 4.30GHz (4 Cores / 8 Threads), Motherboard: ASRock H610M-HDV/M.2 R2.0 (6.03 BIOS), Chipset: Intel Device 7aa7, Memory: 4096MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: Intel ADL-S GT1 3GB (1400MHz), Audio: Realtek ALC897, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.15.0-89-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1366x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x2e
Python Notes: Python 3.8.10
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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: Not affected + tsx_async_abort: Not affected

H610-i312100-1OpenBenchmarking.orgPhoronix Test SuiteIntel Core i3-12100 @ 4.30GHz (4 Cores / 8 Threads)ASRock H610M-HDV/M.2 R2.0 (6.03 BIOS)Intel Device 7aa74096MB1000GB Western Digital WDS100T2B0AIntel ADL-S GT1 3GB (1400MHz)Realtek ALC897Realtek RTL8111/8168/8411Ubuntu 20.045.15.0-89-generic (x86_64)GNOME Shell 3.36.9X Server 1.20.134.6 Mesa 21.2.61.2.182GCC 9.4.0ext41366x768ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionH610-i312100-1 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: 0x2e - Python 3.8.10- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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: Not affected + tsx_async_abort: Not affected

H610-i312100-1whisper-cpp: ggml-medium.en - 2016 State of the Uniondeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamscikit-learn: Sparse Rand Projections / 100 Iterationsscikit-learn: Kernel PCA Solvers / Time vs. N Componentscaffe: GoogleNet - CPU - 1000scikit-learn: SAGAdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamscikit-learn: GLMscikit-learn: Hist Gradient Boosting Higgs Bosonwhisper-cpp: ggml-small.en - 2016 State of the Unionscikit-learn: Lassoscikit-learn: Covertype Dataset Benchmarkplaidml: No - Inference - ResNet 50 - CPUscikit-learn: Hist Gradient Boosting Threadingcaffe: AlexNet - CPU - 1000scikit-learn: TSNE MNIST Datasetpytorch: CPU - 512 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lscikit-learn: Kernel PCA Solvers / Time vs. N Samplespytorch: CPU - 32 - ResNet-50scikit-learn: Feature Expansionsonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelscikit-learn: Plot Polynomial Kernel Approximationonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardxnnpack: QU8MobileNetV3Smallxnnpack: QU8MobileNetV3Largexnnpack: QU8MobileNetV2xnnpack: FP16MobileNetV3Smallxnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV2xnnpack: FP32MobileNetV3Smallxnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV2onnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelscikit-learn: Plot Lasso Pathonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardpytorch: CPU - 512 - ResNet-152pytorch: CPU - 64 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 32 - ResNet-152pytorch: CPU - 16 - ResNet-152scikit-learn: Plot Singular Value Decompositionscikit-learn: Plot Hierarchicalplaidml: No - Inference - VGG16 - CPUonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardwhisper-cpp: ggml-base.en - 2016 State of the Unionnumenta-nab: KNN CADpytorch: CPU - 1 - Efficientnet_v2_lscikit-learn: Treenumenta-nab: Earthgecko Skylinecaffe: GoogleNet - CPU - 200numenta-nab: Bayesian Changepointscikit-learn: Plot OMP vs. LARSmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3mnn: nasnetncnn: CPU - FastestDetncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenettnn: CPU - DenseNetscikit-learn: SGD Regressionscikit-learn: Plot Neighborspytorch: CPU - 16 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 512 - ResNet-50pytorch: CPU - 256 - ResNet-50ncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetnumpy: scikit-learn: Hist Gradient Boostingscikit-learn: Sample Without Replacementonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelscikit-learn: LocalOutlierFactoropencv: DNN - Deep Neural Networkonednn: Deconvolution Batch shapes_1d - CPUcaffe: GoogleNet - CPU - 100onnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardpytorch: CPU - 1 - ResNet-152scikit-learn: Sparsifyonednn: Recurrent Neural Network Training - CPUcaffe: AlexNet - CPU - 200mlpack: scikit_icascikit-learn: MNIST Datasetonednn: Recurrent Neural Network Inference - CPUscikit-learn: Hist Gradient Boosting Adultonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Paralleldeepspeech: CPUscikit-learn: Plot Wardscikit-learn: Text Vectorizersopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUscikit-learn: 20 Newsgroups / Logistic Regressionpytorch: CPU - 1 - ResNet-50openvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Paralleltensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2onnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Standardopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUtensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: SqueezeNetopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUtensorflow-lite: Mobilenet Quantopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUscikit-learn: Plot Incremental PCAopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardnumenta-nab: Relative Entropynumenta-nab: Contextual Anomaly Detector OSEdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamcaffe: AlexNet - CPU - 100deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - 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 Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-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: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamrbenchmark: scikit-learn: Hist Gradient Boosting Categorical Onlymlpack: scikit_svmonednn: IP Shapes 1D - CPUtnn: CPU - MobileNet v2numenta-nab: Windowed Gaussiantnn: CPU - SqueezeNet v1.1onednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUtnn: CPU - SqueezeNet v2onednn: Deconvolution Batch shapes_3d - CPUlczero: BLASIntel ADL-S GT1 - Intel Core i3-121002280.50283211288.57800.0070905.082319.4721038320728.144108889.84520.0092611.356138.505753.36065492.674446.7234.62336.099445933324.5524.484.504.524.514.55276.87812.56241.4751975.360.512476233.5611353.240.7425327281974216396533963444130254845545187.6895.34494226.07819.212353.2627130.8147.915026.176.236.226.246.33199.818186.5548.86196.4325.10110246.28971245.0888.1039.661209.16120646247.477134.66433.5073.3732.7054.74426.3122.9001.1889.0723.31135.496.5717.4240.1226.7112.6312.34109.9216.130.628.153.532.253.185.3521.502446.578119.971105.44412.5712.6912.7612.913.30136.236.5317.4939.8026.9712.5412.25111.1215.830.617.993.192.213.195.2921.05463.1796.57995.57186.697711.540283.8732718510.753310341157.790017.312111.3474.9825708.979022964.7464.5623071.3160.21426.294638.042287.5184052.21951.9993213.281.2449.52424.89759.245.2619.871950.3149225.4654.43575397.4710.06398.5010.0419.560951.1188267.4414.9517.848556.025164931.860949.017.362757.592063.2763.19219.1018.2412005.23574.974322.7119.10208.845198.0723.99166.7145.04345.2288.4119.80201.9060.2166.4018.66214.214.80833.3463.8562.614.77472209.44729.24136.747.79513.0412.09330.424.28771233.2540.3710592.678.19737122.0081.143481.927.00536142.73820.59652.86012.1290164.65146.8777145.27404462225.556378.189115.410764.8531207.67294.8149399.50035.0039490.79774.0749485.37574.1179231.80644.3138230.82794.332138.759651.573258.097334.410531.011232.24165.3924369.35833.3220300.112183.741623.876621.024347.551642.630423.454421.058747.473938.677551.68670.184714.58514.516.00601201.10911.696166.13126.699844.143846.20510.3718OpenBenchmarking.org

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: SGDOneClassSVM

Intel ADL-S GT1 - Intel Core i3-12100: 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: Isolation Forest

Intel ADL-S GT1 - Intel Core i3-12100: 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.

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-medium.en - Input: 2016 State of the UnionIntel ADL-S GT1 - Intel Core i3-121005001000150020002500SE +/- 3.55, N = 32280.501. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2

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: Plot Fast KMeans

Intel ADL-S GT1 - Intel Core i3-12100: 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.

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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-1210050K100K150K200K250KSE +/- 2251.32, N = 9211288.58

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121000.00160.00320.00480.00640.008SE +/- 0.0001, N = 90.0070

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: Sparse Random Projections / 100 IterationsIntel ADL-S GT1 - Intel Core i3-121002004006008001000SE +/- 0.87, N = 3905.081. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N ComponentsIntel ADL-S GT1 - Intel Core i3-1210070140210280350SE +/- 14.09, N = 9319.471. (F9X) gfortran options: -O0

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: GoogleNet - Acceleration: CPU - Iterations: 1000Intel ADL-S GT1 - Intel Core i3-12100200K400K600K800K1000KSE +/- 3248.77, N = 310383201. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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: SAGAIntel ADL-S GT1 - Intel Core i3-12100160320480640800SE +/- 0.42, N = 3728.141. (F9X) gfortran options: -O0

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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210020K40K60K80K100KSE +/- 1162.79, N = 9108889.85

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121000.00210.00420.00630.00840.0105SE +/- 0.0001, N = 90.0092

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 ADL-S GT1 - Intel Core i3-12100130260390520650SE +/- 0.96, N = 3611.361. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Higgs BosonIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 1.02, N = 12138.511. (F9X) gfortran options: -O0

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-small.en - Input: 2016 State of the UnionIntel ADL-S GT1 - Intel Core i3-12100160320480640800SE +/- 0.45, N = 3753.361. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2

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: LassoIntel ADL-S GT1 - Intel Core i3-12100110220330440550SE +/- 1.04, N = 3492.671. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Covertype Dataset BenchmarkIntel ADL-S GT1 - Intel Core i3-12100100200300400500SE +/- 0.14, N = 3446.721. (F9X) gfortran options: -O0

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: ResNet 50 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001.03952.0793.11854.1585.1975SE +/- 0.01, N = 34.62

Mlpack Benchmark

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

Benchmark: scikit_qda

Intel ADL-S GT1 - Intel Core i3-12100: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Benchmark: scikit_linearridgeregression

Intel ADL-S GT1 - Intel Core i3-12100: 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: Hist Gradient Boosting ThreadingIntel ADL-S GT1 - Intel Core i3-1210070140210280350SE +/- 3.75, N = 3336.101. (F9X) gfortran options: -O0

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: 1000Intel ADL-S GT1 - Intel Core i3-12100100K200K300K400K500KSE +/- 4664.71, N = 34459331. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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: TSNE MNIST DatasetIntel ADL-S GT1 - Intel Core i3-1210070140210280350SE +/- 0.43, N = 3324.551. (F9X) gfortran options: -O0

Benchmark: Isotonic / Perturbed Logarithm

Intel ADL-S GT1 - Intel Core i3-12100: 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: Isotonic / Pathological

Intel ADL-S GT1 - Intel Core i3-12100: 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.

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-121001.0082.0163.0244.0325.04SE +/- 0.04, N = 34.48MIN: 3.37 / MAX: 4.59

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-121001.01252.0253.03754.055.0625SE +/- 0.02, N = 34.50MIN: 3.35 / MAX: 4.57

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-121001.0172.0343.0514.0685.085SE +/- 0.01, N = 34.52MIN: 3.17 / MAX: 4.6

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-121001.01482.02963.04444.05925.074SE +/- 0.04, N = 34.51MIN: 3.16 / MAX: 4.61

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-121001.02382.04763.07144.09525.119SE +/- 0.01, N = 34.55MIN: 3.32 / MAX: 4.61

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: Kernel PCA Solvers / Time vs. N SamplesIntel ADL-S GT1 - Intel Core i3-1210060120180240300SE +/- 0.57, N = 3276.881. (F9X) gfortran options: -O0

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.11, N = 812.56MIN: 7.8 / MAX: 13.33

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: Feature ExpansionsIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.42, N = 3241.481. (F9X) gfortran options: -O0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100400800120016002000SE +/- 57.61, N = 151975.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121000.11530.23060.34590.46120.5765SE +/- 0.015328, N = 150.5124761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100400800120016002000SE +/- 57.61, N = 151975.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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: Plot Polynomial Kernel ApproximationIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.21, N = 3233.561. (F9X) gfortran options: -O0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210030060090012001500SE +/- 26.80, N = 151353.241. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121000.16710.33420.50130.66840.8355SE +/- 0.012881, N = 150.7425321. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210030060090012001500SE +/- 26.80, N = 151353.241. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3SmallIntel ADL-S GT1 - Intel Core i3-12100160320480640800SE +/- 0.67, N = 37281. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV3LargeIntel ADL-S GT1 - Intel Core i3-12100400800120016002000SE +/- 20.30, N = 319741. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: QU8MobileNetV2Intel ADL-S GT1 - Intel Core i3-121005001000150020002500SE +/- 21.07, N = 321631. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3SmallIntel ADL-S GT1 - Intel Core i3-121002004006008001000SE +/- 5.84, N = 39651. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV3LargeIntel ADL-S GT1 - Intel Core i3-121007001400210028003500SE +/- 40.00, N = 333961. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP16MobileNetV2Intel ADL-S GT1 - Intel Core i3-12100700140021002800350034441. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3SmallIntel ADL-S GT1 - Intel Core i3-1210030060090012001500SE +/- 14.19, N = 313021. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV3LargeIntel ADL-S GT1 - Intel Core i3-1210012002400360048006000SE +/- 28.00, N = 354841. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK 2cd86bModel: FP32MobileNetV2Intel ADL-S GT1 - Intel Core i3-1210012002400360048006000SE +/- 15.31, N = 355451. (CXX) g++ options: -O3 -lrt -pthread -lpthread -lm

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: Isotonic / Logistic

Intel ADL-S GT1 - Intel Core i3-12100: 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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 2.89, N = 15187.691. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121001.20262.40523.60784.81046.013SE +/- 0.07908, N = 155.344941. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 2.89, N = 15187.691. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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: Plot Lasso PathIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.40, N = 3226.081. (F9X) gfortran options: -O0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.90, N = 1519.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 1.87, N = 1553.261. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.90, N = 1519.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 8.08, N = 14130.811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.33732, N = 147.915021. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 8.08, N = 14130.811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.03, N = 36.17MIN: 4.17 / MAX: 6.34

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.03, N = 36.23MIN: 3.95 / MAX: 6.36

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.02, N = 36.22MIN: 4.3 / MAX: 6.36

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 32 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.03, N = 36.24MIN: 4.36 / MAX: 6.39

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.04, N = 36.33MIN: 4.35 / MAX: 6.45

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: Plot Singular Value DecompositionIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 0.02, N = 3199.821. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot HierarchicalIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 0.37, N = 3186.551. (F9X) gfortran options: -O0

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 ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.09, N = 38.86

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 2.83, N = 12196.431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001.14772.29543.44314.59085.7385SE +/- 0.06535, N = 125.101101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 2.83, N = 12196.431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

Whisper.cpp

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.6.2Model: ggml-base.en - Input: 2016 State of the UnionIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.15, N = 3246.291. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread -msse3 -mssse3 -mavx -mf16c -mfma -mavx2

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 ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.93, N = 3245.09

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.08, N = 58.10MIN: 5.47 / MAX: 8.32

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: TreeIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.30, N = 1539.661. (F9X) gfortran options: -O0

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: Earthgecko SkylineIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.51, N = 3209.16

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: GoogleNet - Acceleration: CPU - Iterations: 200Intel ADL-S GT1 - Intel Core i3-1210040K80K120K160K200KSE +/- 44.14, N = 32064621. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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: Bayesian ChangepointIntel ADL-S GT1 - Intel Core i3-121001122334455SE +/- 0.32, N = 1347.48

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: Plot OMP vs. LARSIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.10, N = 3134.661. (F9X) gfortran options: -O0

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: inception-v3Intel ADL-S GT1 - Intel Core i3-12100816243240SE +/- 0.07, N = 333.51MIN: 32.99 / MAX: 1091. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenet-v1-1.0Intel ADL-S GT1 - Intel Core i3-121000.75891.51782.27673.03563.7945SE +/- 0.048, N = 33.373MIN: 3.24 / MAX: 29.191. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: MobileNetV2_224Intel ADL-S GT1 - Intel Core i3-121000.60861.21721.82582.43443.043SE +/- 0.007, N = 32.705MIN: 2.65 / MAX: 4.631. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: SqueezeNetV1.0Intel ADL-S GT1 - Intel Core i3-121001.06742.13483.20224.26965.337SE +/- 0.009, N = 34.744MIN: 4.68 / MAX: 20.91. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: resnet-v2-50Intel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.04, N = 326.31MIN: 25.83 / MAX: 99.471. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: squeezenetv1.1Intel ADL-S GT1 - Intel Core i3-121000.65251.3051.95752.613.2625SE +/- 0.015, N = 32.900MIN: 2.83 / MAX: 42.331. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: mobilenetV3Intel ADL-S GT1 - Intel Core i3-121000.26730.53460.80191.06921.3365SE +/- 0.047, N = 31.188MIN: 1.12 / MAX: 49.71. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.9.b11b7037dModel: nasnetIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.022, N = 39.072MIN: 8.93 / MAX: 29.561. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -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: FastestDetIntel ADL-S GT1 - Intel Core i3-121000.74481.48962.23442.97923.724SE +/- 0.05, N = 43.31MIN: 3.17 / MAX: 7.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.38, N = 4135.49MIN: 134.44 / MAX: 253.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.03, N = 46.57MIN: 6.47 / MAX: 15.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.08, N = 417.42MIN: 17.17 / MAX: 33.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.06, N = 440.12MIN: 39.72 / MAX: 83.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50Intel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.11, N = 426.71MIN: 26.31 / MAX: 69.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 412.63MIN: 12.45 / MAX: 50.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 412.34MIN: 12.22 / MAX: 14.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16Intel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.09, N = 4109.92MIN: 108.76 / MAX: 150.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.28, N = 416.13MIN: 15.65 / MAX: 75.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceIntel ADL-S GT1 - Intel Core i3-121000.13950.2790.41850.5580.6975SE +/- 0.00, N = 40.62MIN: 0.59 / MAX: 0.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.06, N = 48.15MIN: 7.89 / MAX: 41.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetIntel ADL-S GT1 - Intel Core i3-121000.79431.58862.38293.17723.9715SE +/- 0.25, N = 43.53MIN: 3.13 / MAX: 39.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2Intel ADL-S GT1 - Intel Core i3-121000.50631.01261.51892.02522.5315SE +/- 0.03, N = 42.25MIN: 2.16 / MAX: 18.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3Intel ADL-S GT1 - Intel Core i3-121000.71551.4312.14652.8623.5775SE +/- 0.02, N = 43.18MIN: 3.1 / MAX: 5.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2Intel ADL-S GT1 - Intel Core i3-121001.20382.40763.61144.81526.019SE +/- 0.04, N = 45.35MIN: 5.1 / MAX: 16.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.26, N = 421.50MIN: 20.87 / MAX: 110.781. (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 ADL-S GT1 - Intel Core i3-121005001000150020002500SE +/- 1.75, N = 32446.58MIN: 2392.91 / MAX: 2547.471. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

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: SGD RegressionIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.56, N = 3119.971. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot NeighborsIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.15, N = 3105.441. (F9X) gfortran options: -O0

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 16 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.11, N = 312.57MIN: 8.58 / MAX: 12.97

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.12, N = 312.69MIN: 8.56 / MAX: 13.22

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.18, N = 312.76MIN: 7.94 / MAX: 13.36

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.09, N = 312.91MIN: 8.58 / MAX: 13.25

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: Vulkan GPU - Model: FastestDetIntel ADL-S GT1 - Intel Core i3-121000.74251.4852.22752.973.7125SE +/- 0.02, N = 33.30MIN: 3.23 / MAX: 3.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.09, N = 3136.23MIN: 134.17 / MAX: 308.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.00, N = 36.53MIN: 6.48 / MAX: 6.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.03, N = 317.49MIN: 17.21 / MAX: 58.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.14, N = 339.80MIN: 39.37 / MAX: 78.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50Intel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.29, N = 326.97MIN: 26.39 / MAX: 123.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 312.54MIN: 12.43 / MAX: 14.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 312.25MIN: 12.15 / MAX: 12.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16Intel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.29, N = 3111.12MIN: 109.05 / MAX: 253.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.04, N = 315.83MIN: 15.64 / MAX: 54.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceIntel ADL-S GT1 - Intel Core i3-121000.13730.27460.41190.54920.6865SE +/- 0.00, N = 30.61MIN: 0.59 / MAX: 0.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0Intel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.02, N = 37.99MIN: 7.85 / MAX: 10.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetIntel ADL-S GT1 - Intel Core i3-121000.71781.43562.15342.87123.589SE +/- 0.02, N = 23.19MIN: 3.12 / MAX: 4.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2Intel ADL-S GT1 - Intel Core i3-121000.49730.99461.49191.98922.4865SE +/- 0.01, N = 32.21MIN: 2.16 / MAX: 3.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Intel ADL-S GT1 - Intel Core i3-121000.71781.43562.15342.87123.589SE +/- 0.00, N = 33.19MIN: 3.11 / MAX: 4.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Intel ADL-S GT1 - Intel Core i3-121001.19032.38063.57094.76125.9515SE +/- 0.02, N = 35.29MIN: 5.08 / MAX: 7.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.03, N = 321.05MIN: 20.81 / MAX: 24.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -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 ADL-S GT1 - Intel Core i3-12100100200300400500SE +/- 0.39, N = 3463.17

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: Hist Gradient BoostingIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.18, N = 396.581. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sample Without ReplacementIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.11, N = 395.571. (F9X) gfortran options: -O0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.89, N = 686.701. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.12, N = 611.541. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.89, N = 686.701. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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: LocalOutlierFactorIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.08, N = 383.871. (F9X) gfortran options: -O0

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 ADL-S GT1 - Intel Core i3-121006K12K18K24K30KSE +/- 832.87, N = 12271851. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

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 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.10, N = 1510.75MIN: 8.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: GoogleNet - Acceleration: CPU - Iterations: 100Intel ADL-S GT1 - Intel Core i3-1210020K40K60K80K100KSE +/- 148.50, N = 31034111. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.65, N = 557.791. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.19, N = 517.311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.65, N = 557.791. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152Intel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.03, N = 311.34MIN: 7.58 / MAX: 11.54

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: SparsifyIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.27, N = 374.981. (F9X) gfortran options: -O0

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 3.4Harness: Recurrent Neural Network Training - Engine: CPUIntel ADL-S GT1 - Intel Core i3-1210012002400360048006000SE +/- 4.76, N = 35708.97MIN: 5677.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 200Intel ADL-S GT1 - Intel Core i3-1210020K40K60K80K100KSE +/- 881.92, N = 3902291. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.72, N = 464.74

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: MNIST DatasetIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.04, N = 364.561. (F9X) gfortran options: -O0

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 3.4Harness: Recurrent Neural Network Inference - Engine: CPUIntel ADL-S GT1 - Intel Core i3-121007001400210028003500SE +/- 12.33, N = 33071.31MIN: 3037.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: Hist Gradient Boosting AdultIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.09, N = 360.211. (F9X) gfortran options: -O0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.28, N = 426.291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.42, N = 438.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.28, N = 426.291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.60, N = 387.52

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: Plot WardIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.10, N = 352.221. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Text VectorizersIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.05, N = 352.001. (F9X) gfortran options: -O0

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 2024.0Model: Face Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121007001400210028003500SE +/- 1.80, N = 33213.28MIN: 2964.37 / MAX: 3356.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121000.2790.5580.8371.1161.395SE +/- 0.00, N = 31.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 20 Newsgroups / Logistic RegressionIntel ADL-S GT1 - Intel Core i3-121001122334455SE +/- 0.02, N = 349.521. (F9X) gfortran options: -O0

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50Intel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.26, N = 424.89MIN: 11.71 / MAX: 25.9

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 2024.0Model: Face Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100160320480640800SE +/- 1.39, N = 3759.24MIN: 716.66 / MAX: 920.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001.18352.3673.55054.7345.9175SE +/- 0.01, N = 35.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.03, N = 319.871. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121001122334455SE +/- 0.08, N = 350.311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.03, N = 319.871. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.70, N = 3225.471. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121000.9981.9962.9943.9924.99SE +/- 0.03335, N = 34.435751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 1.70, N = 3225.471. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Person Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210090180270360450SE +/- 1.13, N = 3397.47MIN: 223.86 / MAX: 566.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.03, N = 310.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210090180270360450SE +/- 0.71, N = 3398.50MIN: 293.03 / MAX: 564.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 310.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.19, N = 319.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.51, N = 351.121. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.19, N = 319.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210060120180240300SE +/- 0.35, N = 3267.44MIN: 221.5 / MAX: 472.421. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.02, N = 314.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.01, N = 317.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.04, N = 356.031. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.01, N = 317.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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: Inception V4Intel ADL-S GT1 - Intel Core i3-1210014K28K42K56K70KSE +/- 110.99, N = 364931.8

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Intel ADL-S GT1 - Intel Core i3-1210013K26K39K52K65KSE +/- 49.41, N = 360949.0

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.01, N = 317.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.02, N = 357.591. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.01, N = 317.361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.22, N = 363.27MIN: 31.99 / MAX: 132.51. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.23, N = 363.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.53, N = 3219.10MIN: 120.84 / MAX: 389.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.04, N = 318.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: NASNet MobileIntel ADL-S GT1 - Intel Core i3-121003K6K9K12K15KSE +/- 3.59, N = 312005.2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatIntel ADL-S GT1 - Intel Core i3-121008001600240032004000SE +/- 12.76, N = 33574.97

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetIntel ADL-S GT1 - Intel Core i3-121009001800270036004500SE +/- 12.96, N = 34322.71

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 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.06, N = 319.10MIN: 10.05 / MAX: 69.61. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.74, N = 3208.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: Mobilenet QuantIntel ADL-S GT1 - Intel Core i3-1210011002200330044005500SE +/- 9.03, N = 35198.07

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 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.32, N = 323.99MIN: 13.37 / MAX: 116.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 2.19, N = 3166.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: Plot Incremental PCAIntel ADL-S GT1 - Intel Core i3-121001020304050SE +/- 0.33, N = 345.041. (F9X) gfortran options: -O0

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 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001020304050SE +/- 0.20, N = 345.22MIN: 31.25 / MAX: 119.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.38, N = 388.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.16, N = 319.80MIN: 9.77 / MAX: 70.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 1.60, N = 3201.901. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.22, N = 360.21MIN: 40.96 / MAX: 136.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001530456075SE +/- 0.24, N = 366.401. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.07, N = 318.66MIN: 9.8 / MAX: 90.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.79, N = 3214.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001.082.163.244.325.4SE +/- 0.02, N = 34.80MIN: 3.51 / MAX: 52.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121002004006008001000SE +/- 3.58, N = 3833.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.06, N = 363.85MIN: 30.33 / MAX: 201.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.06, N = 362.611. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121001.07432.14863.22294.29725.3715SE +/- 0.05286, N = 34.774721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 2.29, N = 3209.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-121001.07432.14863.22294.29725.3715SE +/- 0.05286, N = 34.774721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Weld Porosity Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100714212835SE +/- 0.06, N = 329.24MIN: 19.89 / MAX: 66.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.25, N = 3136.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.01, N = 37.79MIN: 4.62 / MAX: 55.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-12100110220330440550SE +/- 0.62, N = 3513.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.09, N = 312.09MIN: 5.92 / MAX: 79.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-1210070140210280350SE +/- 2.36, N = 3330.421. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121000.96471.92942.89413.85884.8235SE +/- 0.04898, N = 34.287711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 2.63, N = 3233.251. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-121000.96471.92942.89413.85884.8235SE +/- 0.04898, N = 34.287711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121000.08330.16660.24990.33320.4165SE +/- 0.00, N = 30.37MIN: 0.24 / MAX: 45.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121002K4K6K8K10KSE +/- 11.73, N = 310592.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.09036, N = 38.197371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 1.34, N = 3122.011. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.09036, N = 38.197371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121000.25650.5130.76951.0261.2825SE +/- 0.01, N = 31.14MIN: 0.58 / MAX: 29.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUIntel ADL-S GT1 - Intel Core i3-121007001400210028003500SE +/- 28.02, N = 33481.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.04100, N = 37.005361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.84, N = 3142.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.04100, N = 37.005361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

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: Relative EntropyIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.18, N = 820.60

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.27, N = 352.86

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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.00, N = 312.13

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 0.07, N = 3164.65

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: Plot Non-Negative Matrix Factorization

Intel ADL-S GT1 - Intel Core i3-12100: 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:

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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.0159, N = 36.8777

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100306090120150SE +/- 0.34, N = 3145.27

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 ADL-S GT1 - Intel Core i3-1210010K20K30K40K50KSE +/- 405.55, N = 3446221. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.02, N = 325.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.07, N = 378.19

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.01, N = 315.41

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121001428425670SE +/- 0.06, N = 364.85

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.45, N = 3207.67

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121001.08342.16683.25024.33365.417SE +/- 0.0104, N = 34.8149

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-1210090180270360450SE +/- 3.23, N = 3399.50

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121001.12592.25183.37774.50365.6295SE +/- 0.0404, N = 35.0039

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100110220330440550SE +/- 1.50, N = 3490.80

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121000.91691.83382.75073.66764.5845SE +/- 0.0124, N = 34.0749

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100110220330440550SE +/- 2.32, N = 3485.38

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121000.92651.8532.77953.7064.6325SE +/- 0.0219, N = 34.1179

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.21, N = 3231.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121000.97061.94122.91183.88244.853SE +/- 0.0039, N = 34.3138

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210050100150200250SE +/- 0.31, N = 3230.83

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121000.97471.94942.92413.89884.8735SE +/- 0.0059, N = 34.3321

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.11, N = 338.76

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.15, N = 351.57

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121001326395265SE +/- 0.19, N = 358.10

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100816243240SE +/- 0.12, N = 334.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100714212835SE +/- 0.04, N = 331.01

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100714212835SE +/- 0.05, N = 332.24

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121001.21332.42663.63994.85326.0665SE +/- 0.0167, N = 35.3924

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-1210080160240320400SE +/- 1.14, N = 3369.36

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121000.74751.4952.24252.993.7375SE +/- 0.0131, N = 33.3220

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-1210070140210280350SE +/- 1.17, N = 3300.11

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-1210020406080100SE +/- 0.10, N = 383.74

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.03, N = 323.88

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.02, N = 321.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121001122334455SE +/- 0.05, N = 347.55

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121001020304050SE +/- 0.02, N = 342.63

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.01, N = 323.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-12100510152025SE +/- 0.02, N = 321.06

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamIntel ADL-S GT1 - Intel Core i3-121001122334455SE +/- 0.04, N = 347.47

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-12100918273645SE +/- 0.14, N = 338.68

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamIntel ADL-S GT1 - Intel Core i3-121001224364860SE +/- 0.19, N = 351.69

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 ADL-S GT1 - Intel Core i3-121000.04160.08320.12480.16640.208SE +/- 0.0015, N = 30.18471. R scripting front-end version 3.6.3 (2020-02-29)

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: Hist Gradient Boosting Categorical OnlyIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.10, N = 314.591. (F9X) gfortran options: -O0

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmIntel ADL-S GT1 - Intel Core i3-1210048121620SE +/- 0.03, N = 314.51

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 3.4Harness: IP Shapes 1D - Engine: CPUIntel ADL-S GT1 - Intel Core i3-12100246810SE +/- 0.01732, N = 36.00601MIN: 5.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: MobileNet v2Intel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 0.11, N = 3201.11MIN: 198.48 / MAX: 216.21. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

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: RCV1 Logreg Convergencet

Intel ADL-S GT1 - Intel Core i3-12100: 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

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: Windowed GaussianIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.02, N = 311.70

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: SqueezeNet v1.1Intel ADL-S GT1 - Intel Core i3-121004080120160200SE +/- 0.09, N = 3166.13MIN: 162.86 / MAX: 170.171. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

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 3.4Harness: IP Shapes 3D - Engine: CPUIntel ADL-S GT1 - Intel Core i3-12100612182430SE +/- 0.03, N = 326.70MIN: 26.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUIntel ADL-S GT1 - Intel Core i3-121001020304050SE +/- 0.43, N = 344.14MIN: 43.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: SqueezeNet v2Intel ADL-S GT1 - Intel Core i3-121001020304050SE +/- 0.07, N = 346.21MIN: 45.29 / MAX: 48.721. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

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 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUIntel ADL-S GT1 - Intel Core i3-121003691215SE +/- 0.09, N = 310.37MIN: 10.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 ADL-S GT1 - Intel Core i3-12100: The test quit with a non-zero exit status. E: AttributeError: module 'numpy' has no attribute 'typeDict'

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: Plot Parallel Pairwise

Intel ADL-S GT1 - Intel Core i3-12100: 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

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 ADL-S GT1 - Intel Core i3-12100: The test quit with a non-zero exit status. E: ImportError: initialization failed

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 ADL-S GT1 - Intel Core i3-12100: 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

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: Glmnet

Intel ADL-S GT1 - Intel Core i3-12100: 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'

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: P3B1

Intel ADL-S GT1 - Intel Core i3-12100: The test quit with a non-zero exit status. E: ImportError: initialization failed

Benchmark: P3B2

Intel ADL-S GT1 - Intel Core i3-12100: The test quit with a non-zero exit status. E: ImportError: initialization failed

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.

Device: CPU - Batch Size: 1 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 1 - Model: GoogLeNet

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: CPU - Batch Size: 32 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 1 - Model: ResNet-50

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: CPU - Batch Size: 1 - Model: AlexNet

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: CPU - Batch Size: 1 - Model: ResNet-50

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: CPU - Batch Size: 1 - Model: GoogLeNet

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 64 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 32 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 16 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: CPU - Batch Size: 64 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 1 - Model: VGG-16

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

Device: GPU - Batch Size: 1 - Model: AlexNet

Intel ADL-S GT1 - Intel Core i3-12100: 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 'absl'

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: yolov4 - Device: CPU - Executor: Parallel

Intel ADL-S GT1 - Intel Core i3-12100: 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 ADL-S GT1 - Intel Core i3-12100: 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

Llama.cpp

Model: llama-2-7b.Q4_0.gguf

Intel ADL-S GT1 - Intel Core i3-12100: 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: main: error: unable to load model

Llamafile

Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU

Intel ADL-S GT1 - Intel Core i3-12100: 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: ./run-wizardcoder: line 2: ./wizardcoder-python-34b-v1.0.Q6_K.llamafile.86: No such file or directory

Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU

Intel ADL-S GT1 - Intel Core i3-12100: 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: ./run-mistral: line 2: ./mistral-7b-instruct-v0.2.Q5_K_M.llamafile.86: No such file or directory

Test: llava-v1.5-7b-q4 - Acceleration: CPU

Intel ADL-S GT1 - Intel Core i3-12100: 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: ./run-llava: line 2: ./llava-v1.6-mistral-7b.Q8_0.llamafile.86: No such file or directory

Llama.cpp

Model: llama-2-70b-chat.Q5_0.gguf

Intel ADL-S GT1 - Intel Core i3-12100: 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: main: error: unable to load model

Model: llama-2-13b.Q4_0.gguf

Intel ADL-S GT1 - Intel Core i3-12100: 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: main: error: unable to load model

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.

Input: 26 Minute Long Talking Sample

Intel ADL-S GT1 - Intel Core i3-12100: 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: ./rnnoise: 2: ./rnnoise-0.2/examples/rnnoise_demo: not found

LeelaChessZero

Backend: BLAS

Intel ADL-S GT1 - Intel Core i3-12100: 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: ./lczero: line 3: ./lc0: No such file or directory

259 Results Shown

Whisper.cpp
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Scikit-Learn:
  Sparse Rand Projections / 100 Iterations
  Kernel PCA Solvers / Time vs. N Components
Caffe
Scikit-Learn
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Synchronous Single-Stream:
    ms/batch
    items/sec
Scikit-Learn:
  GLM
  Hist Gradient Boosting Higgs Boson
Whisper.cpp
Scikit-Learn:
  Lasso
  Covertype Dataset Benchmark
PlaidML
Scikit-Learn
Caffe
Scikit-Learn
PyTorch:
  CPU - 512 - Efficientnet_v2_l
  CPU - 256 - Efficientnet_v2_l
  CPU - 64 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
  CPU - 32 - Efficientnet_v2_l
Scikit-Learn
PyTorch
Scikit-Learn
ONNX Runtime:
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Scikit-Learn
ONNX Runtime:
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
XNNPACK:
  QU8MobileNetV3Small
  QU8MobileNetV3Large
  QU8MobileNetV2
  FP16MobileNetV3Small
  FP16MobileNetV3Large
  FP16MobileNetV2
  FP32MobileNetV3Small
  FP32MobileNetV3Large
  FP32MobileNetV2
ONNX Runtime:
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Scikit-Learn
ONNX Runtime:
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
PyTorch:
  CPU - 512 - ResNet-152
  CPU - 64 - ResNet-152
  CPU - 256 - ResNet-152
  CPU - 32 - ResNet-152
  CPU - 16 - ResNet-152
Scikit-Learn:
  Plot Singular Value Decomposition
  Plot Hierarchical
PlaidML
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
Whisper.cpp
Numenta Anomaly Benchmark
PyTorch
Scikit-Learn
Numenta Anomaly Benchmark
Caffe
Numenta Anomaly Benchmark
Scikit-Learn
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
  nasnet
NCNN:
  CPU - FastestDet
  CPU - vision_transformer
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
TNN
Scikit-Learn:
  SGD Regression
  Plot Neighbors
PyTorch:
  CPU - 16 - ResNet-50
  CPU - 64 - ResNet-50
  CPU - 512 - ResNet-50
  CPU - 256 - ResNet-50
NCNN:
  Vulkan GPU - FastestDet
  Vulkan GPU - vision_transformer
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
Numpy Benchmark
Scikit-Learn:
  Hist Gradient Boosting
  Sample Without Replacement
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Scikit-Learn
OpenCV
oneDNN
Caffe
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
PyTorch
Scikit-Learn
oneDNN
Caffe
Mlpack Benchmark
Scikit-Learn
oneDNN
Scikit-Learn
ONNX Runtime:
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
DeepSpeech
Scikit-Learn:
  Plot Ward
  Text Vectorizers
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
Scikit-Learn
PyTorch
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
ONNX Runtime:
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
  Person Detection FP32 - CPU:
    ms
    FPS
ONNX Runtime:
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
ONNX Runtime:
  T5 Encoder - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
TensorFlow Lite:
  Inception V4
  Inception ResNet V2
ONNX Runtime:
  T5 Encoder - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
TensorFlow Lite:
  NASNet Mobile
  Mobilenet Float
  SqueezeNet
OpenVINO:
  Noise Suppression Poconet-Like FP16 - CPU:
    ms
    FPS
TensorFlow Lite
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
Scikit-Learn
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Person Re-Identification Retail FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
ONNX Runtime:
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
  Face Detection Retail FP16 - CPU:
    ms
    FPS
ONNX Runtime:
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
Numenta Anomaly Benchmark:
  Relative Entropy
  Contextual Anomaly Detector OSE
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
Caffe
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    ms/batch
    items/sec
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Baseline - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    ms/batch
    items/sec
R Benchmark
Scikit-Learn
Mlpack Benchmark
oneDNN
TNN
Numenta Anomaly Benchmark
TNN
oneDNN:
  IP Shapes 3D - CPU
  Convolution Batch Shapes Auto - CPU
TNN
oneDNN

Intel ADL-S GT1 - Intel Core i3-12100

Processor: Intel Core i3-12100 @ 4.30GHz (4 Cores / 8 Threads), Motherboard: ASRock H610M-HDV/M.2 R2.0 (6.03 BIOS), Chipset: Intel Device 7aa7, Memory: 4096MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: Intel ADL-S GT1 3GB (1400MHz), Audio: Realtek ALC897, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.15.0-89-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1366x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x2e
Python Notes: Python 3.8.10
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 August 2024 07:49 by user hertz.