machine-learning-3

2 x AMD EPYC 7F72 24-Core testing with a GIGABYTE MZ62-HD4-00 v01000100 (R18 BIOS) and ASPEED on Rocky Linux 8.6 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2207197-NE-MACHINELE05.

machine-learning-3ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutionmachine-learning-test-32 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads)GIGABYTE MZ62-HD4-00 v01000100 (R18 BIOS)AMD Starship/Matisse8 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2R11000GB INTEL SSDPE2KX010T8 + 960GB Micron_7300_MTFDHBE960TDF + 2 x 1920GB Micron_5210_MTFD + 480GB INTEL SSDSC2KB48ASPEED2 x Intel I350Rocky Linux 8.64.18.0-372.13.1.el8_6.x86_64 (x86_64)GNOME Shell 3.32.2X Server 1.20.11GCC 8.5.0 20210514 + CUDA 11.7xfs800x600OpenBenchmarking.org- Transparent Huge Pages: always- --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x830104d- Python 3.6.8- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

machine-learning-3onednn: 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: CPUrnnoise: mnn: 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: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1plaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - ResNet 50 - CPUnumenta-nab: EXPoSEnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardmlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressionscikit-learn: opencv: DNN - Deep Neural Networkmachine-learning-test-31.8709424.35236.790710.7247250.8937698.461343.167669.052142.019101.252422312.701490.012323.051495.301.936372377.021476.791.90390293.15114.1030121.19814.33519.38479.91525.79325.42324.89689.90077.3135.4830.7431.4832.4742.7413.3074.42728.4947.6322.14108.2087.9561.5673.9078.5639.7832.3637.5037.3445.8114.7176.23666.7047.4424.47102.0293.5968.6080.452822.420315.26778.337282.54316.994.821112.66316.2867.50776.78441.5231029284717320433473954172934441998.22130.1318.485.1013.29282374OpenBenchmarking.org

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUmachine-learning-test-30.4210.8421.2631.6842.105SE +/- 0.01257, N = 31.87094MIN: 1.621. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUmachine-learning-test-3612182430SE +/- 0.02, N = 324.35MIN: 23.691. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-3246810SE +/- 0.28739, N = 156.79071MIN: 3.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-30.16310.32620.48930.65240.8155SE +/- 0.008136, N = 150.724725MIN: 0.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUmachine-learning-test-30.20110.40220.60330.80441.0055SE +/- 0.002759, N = 30.893769MIN: 0.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUmachine-learning-test-3246810SE +/- 0.06736, N = 38.46134MIN: 7.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUmachine-learning-test-30.71271.42542.13812.85083.5635SE +/- 0.03824, N = 153.16766MIN: 2.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-33691215SE +/- 0.32390, N = 159.05214MIN: 4.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-30.45430.90861.36291.81722.2715SE +/- 0.04873, N = 152.01910MIN: 1.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-30.28180.56360.84541.12721.409SE +/- 0.01331, N = 31.25242MIN: 1.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUmachine-learning-test-35001000150020002500SE +/- 20.00, N = 82312.70MIN: 2182.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUmachine-learning-test-330060090012001500SE +/- 6.39, N = 31490.01MIN: 1422.181. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-35001000150020002500SE +/- 15.76, N = 32323.05MIN: 2233.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-330060090012001500SE +/- 7.84, N = 31495.30MIN: 1424.621. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUmachine-learning-test-30.43570.87141.30711.74282.1785SE +/- 0.00883, N = 31.93637MIN: 1.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUmachine-learning-test-35001000150020002500SE +/- 25.82, N = 152377.02MIN: 2119.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUmachine-learning-test-330060090012001500SE +/- 3.98, N = 31476.79MIN: 1420.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUmachine-learning-test-30.42840.85681.28521.71362.142SE +/- 0.01501, N = 31.90390MIN: 1.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkmachine-learning-test-360120180240300SE +/- 1.10, N = 3293.15

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUmachine-learning-test-3306090120150SE +/- 0.36, N = 3114.10

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28machine-learning-test-3510152025SE +/- 0.01, N = 321.201. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3machine-learning-test-348121620SE +/- 0.51, N = 914.34MIN: 10.13 / MAX: 21.091. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1machine-learning-test-3510152025SE +/- 1.35, N = 919.38MIN: 11.71 / MAX: 34.051. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50machine-learning-test-320406080100SE +/- 2.31, N = 979.92MIN: 63.98 / MAX: 148.931. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0machine-learning-test-3612182430SE +/- 1.49, N = 925.79MIN: 16.06 / MAX: 57.841. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224machine-learning-test-3612182430SE +/- 0.47, N = 925.42MIN: 18.01 / MAX: 48.521. (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 1.2Model: mobilenet-v1-1.0machine-learning-test-3612182430SE +/- 1.05, N = 924.90MIN: 16.55 / MAX: 32.81. (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 1.2Model: inception-v3machine-learning-test-320406080100SE +/- 2.24, N = 989.90MIN: 75.49 / MAX: 163.881. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetmachine-learning-test-320406080100SE +/- 3.26, N = 977.31MIN: 57.28 / MAX: 1923.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2machine-learning-test-3816243240SE +/- 0.99, N = 935.48MIN: 28.5 / MAX: 1529.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3machine-learning-test-3714212835SE +/- 1.30, N = 930.74MIN: 23.48 / MAX: 589.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2machine-learning-test-3714212835SE +/- 1.84, N = 931.48MIN: 26.35 / MAX: 303.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetmachine-learning-test-3816243240SE +/- 0.80, N = 932.47MIN: 24.61 / MAX: 149.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0machine-learning-test-31020304050SE +/- 0.66, N = 942.74MIN: 32.51 / MAX: 641.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefacemachine-learning-test-33691215SE +/- 0.39, N = 913.30MIN: 10.27 / MAX: 68.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetmachine-learning-test-320406080100SE +/- 2.47, N = 974.42MIN: 59.56 / MAX: 2183.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16machine-learning-test-3160320480640800SE +/- 33.15, N = 9728.49MIN: 147.73 / MAX: 1373.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18machine-learning-test-31122334455SE +/- 1.44, N = 947.63MIN: 39.04 / MAX: 1027.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetmachine-learning-test-3510152025SE +/- 1.04, N = 922.14MIN: 18.68 / MAX: 656.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50machine-learning-test-320406080100SE +/- 4.48, N = 9108.20MIN: 84.32 / MAX: 4634.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinymachine-learning-test-320406080100SE +/- 1.96, N = 987.95MIN: 73.69 / MAX: 727.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdmachine-learning-test-31428425670SE +/- 0.91, N = 961.56MIN: 50.11 / MAX: 642.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mmachine-learning-test-31632486480SE +/- 1.26, N = 973.90MIN: 64.41 / MAX: 440.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetmachine-learning-test-320406080100SE +/- 3.10, N = 978.56MIN: 61.66 / MAX: 1530.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2machine-learning-test-3918273645SE +/- 1.64, N = 939.78MIN: 29.64 / MAX: 1306.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3machine-learning-test-3816243240SE +/- 0.36, N = 932.36MIN: 25.67 / MAX: 239.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2machine-learning-test-3918273645SE +/- 1.93, N = 937.50MIN: 28.96 / MAX: 1199.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetmachine-learning-test-3918273645SE +/- 0.91, N = 937.34MIN: 28.35 / MAX: 465.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0machine-learning-test-31020304050SE +/- 0.62, N = 945.81MIN: 39.18 / MAX: 230.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefacemachine-learning-test-348121620SE +/- 0.68, N = 914.71MIN: 10.6 / MAX: 652.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetmachine-learning-test-320406080100SE +/- 1.27, N = 976.23MIN: 63.07 / MAX: 1496.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16machine-learning-test-3140280420560700SE +/- 41.35, N = 9666.70MIN: 150.96 / MAX: 1375.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18machine-learning-test-31122334455SE +/- 1.40, N = 947.44MIN: 36.07 / MAX: 1279.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetmachine-learning-test-3612182430SE +/- 2.48, N = 924.47MIN: 19.2 / MAX: 667.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50machine-learning-test-320406080100SE +/- 2.26, N = 9102.02MIN: 83.67 / MAX: 1619.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinymachine-learning-test-320406080100SE +/- 3.56, N = 993.59MIN: 78.58 / MAX: 1680.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdmachine-learning-test-31530456075SE +/- 4.71, N = 968.60MIN: 51.17 / MAX: 3936.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mmachine-learning-test-320406080100SE +/- 3.95, N = 980.45MIN: 66.89 / MAX: 8496.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetmachine-learning-test-36001200180024003000SE +/- 4.45, N = 32822.42MIN: 2755.99 / MAX: 3410.341. (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 v2machine-learning-test-370140210280350SE +/- 3.33, N = 3315.27MIN: 306.88 / MAX: 368.621. (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 v2machine-learning-test-320406080100SE +/- 0.56, N = 378.34MIN: 76.26 / MAX: 86.371. (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 v1.1machine-learning-test-360120180240300SE +/- 2.05, N = 3282.54MIN: 278.72 / MAX: 287.141. (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: CPUmachine-learning-test-348121620SE +/- 0.19, N = 316.99

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUmachine-learning-test-31.08452.1693.25354.3385.4225SE +/- 0.01, N = 34.82

Numenta Anomaly Benchmark

Detector: EXPoSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: EXPoSEmachine-learning-test-32004006008001000SE +/- 25.93, N = 91112.66

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropymachine-learning-test-348121620SE +/- 0.19, N = 316.29

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussianmachine-learning-test-3246810SE +/- 0.090, N = 47.507

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinemachine-learning-test-320406080100SE +/- 0.57, N = 376.78

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointmachine-learning-test-3918273645SE +/- 0.23, N = 341.52

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: Parallelmachine-learning-test-32004006008001000SE +/- 8.58, N = 310291. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: Standardmachine-learning-test-36001200180024003000SE +/- 36.15, N = 328471. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: Parallelmachine-learning-test-34080120160200SE +/- 1.80, N = 31731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: Standardmachine-learning-test-34080120160200SE +/- 3.66, N = 92041. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelmachine-learning-test-3816243240SE +/- 0.29, N = 3331. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: Standardmachine-learning-test-31122334455SE +/- 1.03, N = 12471. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelmachine-learning-test-390180270360450SE +/- 3.06, N = 103951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardmachine-learning-test-390180270360450SE +/- 6.22, N = 124171. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: Parallelmachine-learning-test-36001200180024003000SE +/- 39.18, N = 1229341. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: Standardmachine-learning-test-39001800270036004500SE +/- 94.11, N = 1244191. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icamachine-learning-test-320406080100SE +/- 0.75, N = 398.22

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdamachine-learning-test-3306090120150SE +/- 1.33, N = 5130.13

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmmachine-learning-test-3510152025SE +/- 0.02, N = 318.48

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionmachine-learning-test-31.14752.2953.44254.595.7375SE +/- 0.07, N = 35.10

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1machine-learning-test-33691215SE +/- 0.04, N = 313.29

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.6Test: DNN - Deep Neural Networkmachine-learning-test-320K40K60K80K100KSE +/- 2907.72, N = 13823741. (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