sk3tchy-creator-tst

VMware testing on Debian 11 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2303010-NE-SK3TCHYCR76.

sk3tchy-creator-tstProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelVulkanCompilerFile-SystemScreen ResolutionSystem Layercentos-vm2 x Intel Core i9-9900K (4 Cores)Intel 440BX (6.00 BIOS)Intel 440BX/ZX/DX1 x 4 GB DRAM107GB Virtual diskVMware SVGA IIVMware VMXNET3Debian 115.10.0-21-amd64 (x86_64)1.0.2GCC 10.2.1 20210110ext41176x885VMwareOpenBenchmarking.org- Transparent Huge Pages: always- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - CPU Microcode: 0xea- Python 3.9.2- itlb_multihit: KVM: Mitigation of VMX unsupported + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT Host state unknown + retbleed: Mitigation of IBRS + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

sk3tchy-creator-tstlczero: BLASonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUnumpy: deepspeech: CPUrbenchmark: rnnoise: tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamcaffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200caffe: AlexNet - CPU - 1000caffe: GoogleNet - CPU - 100caffe: GoogleNet - CPU - 200caffe: GoogleNet - CPU - 1000mnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDettnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1plaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - ResNet 50 - CPUnumenta-nab: KNN CADnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Contextual Anomaly Detector OSEscikit-learn: MNIST Datasetscikit-learn: TSNE MNIST Datasetscikit-learn: Sparse Rand Projections, 100 Iterationsopencv: DNN - Deep Neural Networkcentos-vm12686.074708.611282.643532.7487216.467010.190610.592316.79154.012908.523085169.423103.295203.703114.254.205345220.573114.152.27932371.4465.854440.131922.9876449.6695985.414313.64839.428367.1787461.03.9171508.49472.0387490.511745.713643.716425.487139.226914.6138136.76568.1049123.374821.596192.545911.395487.743444.256845.148923.095543.288432.802160.923516.872159.26165.7598345.84003.0853324.098616.4088121.80938.4059118.95713.9141509.88172.0309492.39732527350387253259637781276966378739.5981.5332.63722.8084.3802.9663.43529.07816.624.633.723.534.028.880.9114.5262.6812.499.7925.4425.5117.669.64470.883.63654.98223.54205.42170.09230.97343.0051.27578.673020.88537.33667.051298.50944.39620.86281.728709.22162.713875.532289.27466.231285.8628.935.74340.66036.76920.895226.20162.58561.830109.97337.240165.89013471OpenBenchmarking.org

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLAScentos-vm30060090012001500SE +/- 9.21, N = 312681. (CXX) g++ options: -flto -pthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUcentos-vm246810SE +/- 0.03230, N = 36.07470MIN: 5.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUcentos-vm246810SE +/- 0.01390, N = 38.61128MIN: 8.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUcentos-vm0.59481.18961.78442.37922.974SE +/- 0.00074, N = 32.64353MIN: 2.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUcentos-vm0.61851.2371.85552.4743.0925SE +/- 0.02400, N = 72.74872MIN: 2.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUcentos-vm48121620SE +/- 0.03, N = 316.47MIN: 15.971. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUcentos-vm3691215SE +/- 0.05, N = 310.19MIN: 9.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUcentos-vm3691215SE +/- 0.03, N = 310.59MIN: 10.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUcentos-vm48121620SE +/- 0.06, N = 316.79MIN: 16.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUcentos-vm0.90291.80582.70873.61164.5145SE +/- 0.00809, N = 34.01290MIN: 3.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUcentos-vm246810SE +/- 0.13961, N = 128.52308MIN: 7.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUcentos-vm11002200330044005500SE +/- 25.57, N = 35169.42MIN: 5076.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUcentos-vm7001400210028003500SE +/- 17.09, N = 33103.29MIN: 3032.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUcentos-vm11002200330044005500SE +/- 19.73, N = 35203.70MIN: 5093.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUcentos-vm7001400210028003500SE +/- 12.04, N = 33114.25MIN: 3041.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUcentos-vm0.94621.89242.83863.78484.731SE +/- 0.01449, N = 34.20534MIN: 3.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUcentos-vm11002200330044005500SE +/- 21.04, N = 35220.57MIN: 5124.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUcentos-vm7001400210028003500SE +/- 9.14, N = 33114.15MIN: 3057.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUcentos-vm0.51281.02561.53842.05122.564SE +/- 0.00226, N = 32.27932MIN: 2.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkcentos-vm80160240320400SE +/- 1.45, N = 3371.44

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUcentos-vm1530456075SE +/- 0.16, N = 365.85

R Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterR Benchmarkcentos-vm0.02970.05940.08910.11880.1485SE +/- 0.0002, N = 30.13191. R scripting front-end version 4.0.4 (2021-02-15)

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28centos-vm612182430SE +/- 0.04, N = 322.991. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetcentos-vm14002800420056007000SE +/- 26.61, N = 36449.66

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4centos-vm20K40K60K80K100KSE +/- 137.23, N = 395985.4

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilecentos-vm3K6K9K12K15KSE +/- 62.51, N = 314313.6

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatcentos-vm10002000300040005000SE +/- 8.64, N = 34839.42

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantcentos-vm2K4K6K8K10KSE +/- 9.73, N = 38367.17

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2centos-vm20K40K60K80K100KSE +/- 140.59, N = 387461.0

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamcentos-vm0.88131.76262.64393.52524.4065SE +/- 0.0138, N = 33.9171

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamcentos-vm110220330440550SE +/- 1.59, N = 3508.49

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcentos-vm0.45870.91741.37611.83482.2935SE +/- 0.0081, N = 32.0387

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamcentos-vm110220330440550SE +/- 1.95, N = 3490.51

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamcentos-vm1020304050SE +/- 0.24, N = 345.71

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamcentos-vm1020304050SE +/- 0.22, N = 343.72

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamcentos-vm612182430SE +/- 0.10, N = 325.49

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Streamcentos-vm918273645SE +/- 0.16, N = 339.23

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamcentos-vm48121620SE +/- 0.05, N = 314.61

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamcentos-vm306090120150SE +/- 0.44, N = 3136.77

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamcentos-vm246810SE +/- 0.0303, N = 38.1049

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Streamcentos-vm306090120150SE +/- 0.46, N = 3123.37

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamcentos-vm510152025SE +/- 0.07, N = 321.60

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamcentos-vm20406080100SE +/- 0.28, N = 392.55

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamcentos-vm3691215SE +/- 0.00, N = 311.40

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamcentos-vm20406080100SE +/- 0.03, N = 387.74

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcentos-vm1020304050SE +/- 0.09, N = 344.26

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamcentos-vm1020304050SE +/- 0.09, N = 345.15

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamcentos-vm612182430SE +/- 0.03, N = 323.10

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamcentos-vm1020304050SE +/- 0.06, N = 343.29

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcentos-vm816243240SE +/- 0.01, N = 332.80

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamcentos-vm1428425670SE +/- 0.01, N = 360.92

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamcentos-vm48121620SE +/- 0.03, N = 316.87

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamcentos-vm1326395265SE +/- 0.10, N = 359.26

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamcentos-vm1.2962.5923.8885.1846.48SE +/- 0.0086, N = 35.7598

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamcentos-vm80160240320400SE +/- 0.68, N = 3345.84

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcentos-vm0.69421.38842.08262.77683.471SE +/- 0.0010, N = 33.0853

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamcentos-vm70140210280350SE +/- 0.10, N = 3324.10

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamcentos-vm48121620SE +/- 0.01, N = 316.41

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamcentos-vm306090120150SE +/- 0.04, N = 3121.81

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcentos-vm246810SE +/- 0.0205, N = 38.4059

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamcentos-vm306090120150SE +/- 0.29, N = 3118.96

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamcentos-vm0.88071.76142.64213.52284.4035SE +/- 0.0187, N = 33.9141

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamcentos-vm110220330440550SE +/- 2.54, N = 3509.88

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcentos-vm0.4570.9141.3711.8282.285SE +/- 0.0058, N = 32.0309

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamcentos-vm110220330440550SE +/- 1.41, N = 3492.40

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100centos-vm5K10K15K20K25KSE +/- 62.69, N = 3252731. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200centos-vm11K22K33K44K55KSE +/- 110.33, N = 3503871. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 1000

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 1000centos-vm50K100K150K200K250KSE +/- 438.44, N = 32532591. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100centos-vm14K28K42K56K70KSE +/- 100.74, N = 3637781. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200centos-vm30K60K90K120K150KSE +/- 238.00, N = 31276961. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 1000

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 1000centos-vm140K280K420K560K700KSE +/- 1015.06, N = 36378731. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Mobile Neural Network

Model: nasnet

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetcentos-vm3691215SE +/- 0.092, N = 129.598MIN: 8.18 / MAX: 34.791. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3centos-vm0.34490.68981.03471.37961.7245SE +/- 0.028, N = 121.533MIN: 1.29 / MAX: 23.281. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1centos-vm0.59331.18661.77992.37322.9665SE +/- 0.026, N = 122.637MIN: 2.34 / MAX: 23.411. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50centos-vm510152025SE +/- 0.04, N = 1222.81MIN: 21.78 / MAX: 50.811. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0centos-vm0.98551.9712.95653.9424.9275SE +/- 0.016, N = 124.380MIN: 4.14 / MAX: 26.231. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224centos-vm0.66741.33482.00222.66963.337SE +/- 0.027, N = 122.966MIN: 2.55 / MAX: 23.151. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0centos-vm0.77291.54582.31873.09163.8645SE +/- 0.017, N = 123.435MIN: 3.19 / MAX: 24.991. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3centos-vm714212835SE +/- 0.07, N = 1229.08MIN: 27.99 / MAX: 75.441. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetcentos-vm48121620SE +/- 0.04, N = 316.62MIN: 15.88 / MAX: 65.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2centos-vm1.04182.08363.12544.16725.209SE +/- 0.04, N = 34.63MIN: 4.28 / MAX: 47.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3centos-vm0.8371.6742.5113.3484.185SE +/- 0.04, N = 33.72MIN: 3.54 / MAX: 15.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2centos-vm0.79431.58862.38293.17723.9715SE +/- 0.07, N = 33.53MIN: 3.18 / MAX: 63.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetcentos-vm0.90451.8092.71353.6184.5225SE +/- 0.09, N = 34.02MIN: 3.67 / MAX: 46.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0centos-vm246810SE +/- 0.06, N = 38.88MIN: 8.3 / MAX: 52.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefacecentos-vm0.20480.40960.61440.81921.024SE +/- 0.04, N = 30.91MIN: 0.81 / MAX: 1.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetcentos-vm48121620SE +/- 0.16, N = 314.52MIN: 13.55 / MAX: 69.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16centos-vm1428425670SE +/- 0.08, N = 362.68MIN: 60.77 / MAX: 111.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18centos-vm3691215SE +/- 0.47, N = 312.49MIN: 11.31 / MAX: 60.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetcentos-vm3691215SE +/- 0.12, N = 39.79MIN: 9.18 / MAX: 21.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50centos-vm612182430SE +/- 0.29, N = 325.44MIN: 24.18 / MAX: 71.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinycentos-vm612182430SE +/- 0.04, N = 225.51MIN: 24.44 / MAX: 71.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdcentos-vm48121620SE +/- 0.11, N = 317.66MIN: 16.93 / MAX: 62.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mcentos-vm3691215SE +/- 0.14, N = 39.64MIN: 8.91 / MAX: 53.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformercentos-vm100200300400500SE +/- 0.30, N = 3470.88MIN: 463.72 / MAX: 515.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetcentos-vm0.81681.63362.45043.26724.084SE +/- 0.04, N = 33.63MIN: 3.22 / MAX: 19.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetcentos-vm140280420560700SE +/- 3.23, N = 3654.98MIN: 631.79 / MAX: 701.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2centos-vm50100150200250SE +/- 0.66, N = 3223.54MIN: 210.98 / MAX: 240.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3centos-vm50100150200250SE +/- 0.25, N = 3205.42MIN: 195.53 / MAX: 221.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2centos-vm4080120160200SE +/- 0.27, N = 3170.09MIN: 162.43 / MAX: 186.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetcentos-vm50100150200250SE +/- 0.56, N = 3230.97MIN: 219.26 / MAX: 253.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0centos-vm70140210280350SE +/- 1.25, N = 3343.00MIN: 328.3 / MAX: 362.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefacecentos-vm1224364860SE +/- 0.05, N = 351.27MIN: 46.95 / MAX: 63.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetcentos-vm130260390520650SE +/- 1.32, N = 3578.67MIN: 556.51 / MAX: 638.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16centos-vm6001200180024003000SE +/- 1.29, N = 33020.88MIN: 2995.08 / MAX: 3117.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18centos-vm120240360480600SE +/- 0.32, N = 3537.33MIN: 523.52 / MAX: 592.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetcentos-vm140280420560700SE +/- 0.18, N = 3667.05MIN: 655.5 / MAX: 714.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50centos-vm30060090012001500SE +/- 2.05, N = 31298.50MIN: 1271.83 / MAX: 1359.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinycentos-vm2004006008001000SE +/- 0.37, N = 3944.39MIN: 927.08 / MAX: 987.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdcentos-vm130260390520650SE +/- 0.98, N = 3620.86MIN: 605.38 / MAX: 648.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mcentos-vm60120180240300SE +/- 1.77, N = 3281.72MIN: 271.06 / MAX: 308.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformercentos-vm2K4K6K8K10KSE +/- 0.52, N = 38709.22MIN: 8652.35 / MAX: 8861.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetcentos-vm4080120160200SE +/- 0.16, N = 3162.71MIN: 156.62 / MAX: 177.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetcentos-vm8001600240032004000SE +/- 5.36, N = 33875.53MIN: 3780.95 / MAX: 3989.331. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2centos-vm60120180240300SE +/- 0.12, N = 3289.27MIN: 285.71 / MAX: 298.981. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2centos-vm1530456075SE +/- 0.09, N = 366.23MIN: 65.38 / MAX: 78.771. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1centos-vm60120180240300SE +/- 0.25, N = 3285.86MIN: 284.22 / MAX: 293.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUcentos-vm246810SE +/- 0.09, N = 38.93

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUcentos-vm1.29152.5833.87455.1666.4575SE +/- 0.02, N = 35.74

Numenta Anomaly Benchmark

Detector: KNN CAD

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADcentos-vm70140210280350SE +/- 2.45, N = 3340.66

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropycentos-vm816243240SE +/- 0.31, N = 336.77

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussiancentos-vm510152025SE +/- 0.18, N = 1520.90

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinecentos-vm50100150200250SE +/- 1.22, N = 3226.20

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointcentos-vm1428425670SE +/- 0.40, N = 362.59

Numenta Anomaly Benchmark

Detector: Contextual Anomaly Detector OSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEcentos-vm1428425670SE +/- 1.43, N = 1561.83

Scikit-Learn

Benchmark: MNIST Dataset

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: MNIST Datasetcentos-vm20406080100SE +/- 1.23, N = 3109.97

Scikit-Learn

Benchmark: TSNE MNIST Dataset

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: TSNE MNIST Datasetcentos-vm918273645SE +/- 0.40, N = 1537.24

Scikit-Learn

Benchmark: Sparse Random Projections, 100 Iterations

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: Sparse Random Projections, 100 Iterationscentos-vm4080120160200SE +/- 0.24, N = 3165.89

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.6Test: DNN - Deep Neural Networkcentos-vm3K6K9K12K15KSE +/- 187.15, N = 15134711. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

Phoronix Test Suite v10.8.4