ml_test_results1

wsl testing on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208043-NE-MLTESTRES01.

ml_test_results1ProcessorMemoryDiskGraphicsOSKernelDisplay ServerVulkanCompilerFile-SystemSystem Layerrtx3080_12900KIntel Core i9-12900K (12 Cores / 24 Threads)16GB4 x 275GB Virtual DiskNVIDIA GeForce RTX 3080 10GBUbuntu 20.045.10.16.3-microsoft-standard-WSL2 (x86_64)Wayland1.1.182GCC 9.4.0ext4wslOpenBenchmarking.org- Transparent Huge Pages: always- --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-Av3uEd/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 - CPU Microcode: 0xffffffff- Python 3.9.12- 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ml_test_results1lczero: 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: CPUrnnoise: tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2mnn: 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 - CPUecp-candle: P1B2ecp-candle: P3B1ecp-candle: P3B2numenta-nab: EXPoSEnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointscikit-learn: opencv: DNN - Deep Neural Networkrtx3080_12900K8733.371874.580151.238861.1414810.296748.48455.933457.757151.810622.454893228.291887.173286.901904.801.747863313.031901.011.09774632.1853.6592313.7852118.0227824.610433.31453.483506.2228252.71.5053.21724.5524.8432.9663.68827.70713.313.993.633.693.856.051.7613.2836.6013.0610.1022.8721.0318.2210.65430.58137.48135.86114.99142.62217.8756.20488.702434.37520.87403.911310.27883.04689.50212.732000.468179.55239.151140.44926.558.2621.503403.021480.897212.8169.5244.87275.04616.6295.364OpenBenchmarking.org

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASrtx3080_12900K2004006008001000SE +/- 13.46, N = 98731. (CXX) g++ options: -flto -pthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUrtx3080_12900K0.75871.51742.27613.03483.7935SE +/- 0.23087, N = 153.37187MIN: 2.541. (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: CPUrtx3080_12900K1.03052.0613.09154.1225.1525SE +/- 0.03103, N = 34.58015MIN: 3.991. (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: CPUrtx3080_12900K0.27870.55740.83611.11481.3935SE +/- 0.00413, N = 31.23886MIN: 1.011. (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: CPUrtx3080_12900K0.25680.51360.77041.02721.284SE +/- 0.00236, N = 31.14148MIN: 0.871. (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: CPUrtx3080_12900K3691215SE +/- 0.12, N = 310.30MIN: 6.931. (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: CPUrtx3080_12900K1122334455SE +/- 23.80, N = 1248.48MIN: -5.661. (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: CPUrtx3080_12900K1.3352.674.0055.346.675SE +/- 0.02400, N = 35.93345MIN: 5.031. (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: CPUrtx3080_12900K246810SE +/- 0.00974, N = 37.75715MIN: 7.111. (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: CPUrtx3080_12900K0.40740.81481.22221.62962.037SE +/- 0.02131, N = 31.81062MIN: 1.291. (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: CPUrtx3080_12900K0.55241.10481.65722.20962.762SE +/- 0.01674, N = 32.45489MIN: 1.881. (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: CPUrtx3080_12900K7001400210028003500SE +/- 6.23, N = 33228.29MIN: 2903.81. (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: CPUrtx3080_12900K400800120016002000SE +/- 6.88, N = 31887.17MIN: 1638.561. (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: CPUrtx3080_12900K7001400210028003500SE +/- 3.40, N = 33286.90MIN: 2997.251. (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: CPUrtx3080_12900K400800120016002000SE +/- 11.48, N = 31904.80MIN: 1657.991. (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: CPUrtx3080_12900K0.39330.78661.17991.57321.9665SE +/- 0.01679, N = 31.74786MIN: 1.31. (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: CPUrtx3080_12900K7001400210028003500SE +/- 8.93, N = 33313.03MIN: 3028.051. (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: CPUrtx3080_12900K400800120016002000SE +/- 5.05, N = 31901.01MIN: 1632.671. (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: CPUrtx3080_12900K0.2470.4940.7410.9881.235SE +/- 0.01149, N = 31.09774MIN: 0.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkrtx3080_12900K140280420560700SE +/- 1.41, N = 3632.18

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUrtx3080_12900K1224364860SE +/- 0.04, N = 353.66

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28rtx3080_12900K48121620SE +/- 0.06, N = 313.791. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetrtx3080_12900K5001000150020002500SE +/- 27.20, N = 32118.02

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4rtx3080_12900K6K12K18K24K30KSE +/- 296.94, N = 327824.6

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilertx3080_12900K2K4K6K8K10KSE +/- 42.58, N = 310433.3

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatrtx3080_12900K30060090012001500SE +/- 3.88, N = 31453.48

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantrtx3080_12900K8001600240032004000SE +/- 13.34, N = 33506.22

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2rtx3080_12900K6K12K18K24K30KSE +/- 60.20, N = 328252.7

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3rtx3080_12900K0.33860.67721.01581.35441.693SE +/- 0.016, N = 31.505MIN: 1.11 / MAX: 34.921. (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: squeezenetv1.1rtx3080_12900K0.72381.44762.17142.89523.619SE +/- 0.025, N = 33.217MIN: 2.28 / MAX: 26.031. (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-v2-50rtx3080_12900K612182430SE +/- 0.69, N = 324.55MIN: 18.61 / MAX: 76.371. (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: SqueezeNetV1.0rtx3080_12900K1.08972.17943.26914.35885.4485SE +/- 0.117, N = 34.843MIN: 3.74 / MAX: 28.751. (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_224rtx3080_12900K0.66741.33482.00222.66963.337SE +/- 0.129, N = 32.966MIN: 2.09 / MAX: 37.651. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0rtx3080_12900K0.82981.65962.48943.31924.149SE +/- 0.120, N = 33.688MIN: 2.9 / MAX: 29.61. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3rtx3080_12900K714212835SE +/- 0.27, N = 327.71MIN: 21.63 / MAX: 70.021. (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: mobilenetrtx3080_12900K3691215SE +/- 0.18, N = 1513.31MIN: 9.02 / MAX: 63.461. (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-v2rtx3080_12900K0.89781.79562.69343.59124.489SE +/- 0.09, N = 153.99MIN: 2.69 / MAX: 48.121. (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-v3rtx3080_12900K0.81681.63362.45043.26724.084SE +/- 0.06, N = 153.63MIN: 2.46 / MAX: 43.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2rtx3080_12900K0.83031.66062.49093.32124.1515SE +/- 0.10, N = 153.69MIN: 2.58 / MAX: 36.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetrtx3080_12900K0.86631.73262.59893.46524.3315SE +/- 0.09, N = 153.85MIN: 2.51 / MAX: 39.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0rtx3080_12900K246810SE +/- 0.14, N = 156.05MIN: 4.03 / MAX: 47.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefacertx3080_12900K0.3960.7921.1881.5841.98SE +/- 0.04, N = 151.76MIN: 1.08 / MAX: 35.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetrtx3080_12900K3691215SE +/- 0.13, N = 1513.28MIN: 8.45 / MAX: 83.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16rtx3080_12900K816243240SE +/- 0.22, N = 1536.60MIN: 27.3 / MAX: 188.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18rtx3080_12900K3691215SE +/- 0.09, N = 1413.06MIN: 8.49 / MAX: 52.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetrtx3080_12900K3691215SE +/- 0.08, N = 1510.10MIN: 8.16 / MAX: 81.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50rtx3080_12900K510152025SE +/- 0.15, N = 1522.87MIN: 14.81 / MAX: 184.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyrtx3080_12900K510152025SE +/- 0.36, N = 1521.03MIN: 14.46 / MAX: 71.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdrtx3080_12900K48121620SE +/- 0.16, N = 1518.22MIN: 13.38 / MAX: 146.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mrtx3080_12900K3691215SE +/- 0.28, N = 1510.65MIN: 6.83 / MAX: 73.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetrtx3080_12900K90180270360450SE +/- 0.08, N = 3430.58MIN: 421.54 / MAX: 458.481. (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-v2rtx3080_12900K306090120150SE +/- 0.05, N = 3137.48MIN: 133.02 / MAX: 141.71. (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-v3rtx3080_12900K306090120150SE +/- 0.03, N = 3135.86MIN: 131.13 / MAX: 137.441. (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-v2rtx3080_12900K306090120150SE +/- 0.09, N = 3114.99MIN: 111.82 / MAX: 117.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetrtx3080_12900K306090120150SE +/- 0.02, N = 3142.62MIN: 139.79 / MAX: 144.41. (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-b0rtx3080_12900K50100150200250SE +/- 0.08, N = 3217.87MIN: 215.21 / MAX: 220.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefacertx3080_12900K1326395265SE +/- 0.08, N = 356.20MIN: 53.51 / MAX: 69.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetrtx3080_12900K110220330440550SE +/- 0.08, N = 3488.70MIN: 481.13 / MAX: 497.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16rtx3080_12900K5001000150020002500SE +/- 1.33, N = 32434.37MIN: 2412.9 / MAX: 2463.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18rtx3080_12900K110220330440550SE +/- 0.03, N = 3520.87MIN: 511.73 / MAX: 528.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetrtx3080_12900K90180270360450SE +/- 0.02, N = 3403.91MIN: 392.65 / MAX: 416.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50rtx3080_12900K30060090012001500SE +/- 0.34, N = 31310.27MIN: 1294.24 / MAX: 1324.681. (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-tinyrtx3080_12900K2004006008001000SE +/- 0.19, N = 3883.04MIN: 871.65 / MAX: 909.831. (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_ssdrtx3080_12900K150300450600750SE +/- 0.27, N = 3689.50MIN: 673.93 / MAX: 704.351. (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_400mrtx3080_12900K50100150200250SE +/- 0.05, N = 3212.73MIN: 208.99 / MAX: 215.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetrtx3080_12900K400800120016002000SE +/- 1.15, N = 32000.47MIN: 1950.77 / MAX: 2074.841. (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 v2rtx3080_12900K4080120160200SE +/- 0.12, N = 3179.55MIN: 173.18 / MAX: 204.811. (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 v2rtx3080_12900K918273645SE +/- 0.14, N = 339.15MIN: 37.65 / MAX: 46.521. (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 v1.1rtx3080_12900K306090120150SE +/- 0.13, N = 3140.45MIN: 137.71 / MAX: 150.951. (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: CPUrtx3080_12900K612182430SE +/- 0.21, N = 326.55

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUrtx3080_12900K246810SE +/- 0.02, N = 38.26

ECP-CANDLE

Benchmark: P1B2

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P1B2rtx3080_12900K51015202521.50

ECP-CANDLE

Benchmark: P3B1

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B1rtx3080_12900K90180270360450403.02

ECP-CANDLE

Benchmark: P3B2

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B2rtx3080_12900K100200300400500480.90

Numenta Anomaly Benchmark

Detector: EXPoSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: EXPoSErtx3080_12900K50100150200250SE +/- 2.25, N = 3212.82

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropyrtx3080_12900K3691215SE +/- 0.127, N = 39.524

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussianrtx3080_12900K1.09622.19243.28864.38485.481SE +/- 0.029, N = 34.872

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinertx3080_12900K20406080100SE +/- 0.32, N = 375.05

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepointrtx3080_12900K48121620SE +/- 0.09, N = 316.63

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1rtx3080_12900K1.20692.41383.62074.82766.0345SE +/- 0.038, N = 35.364

Phoronix Test Suite v10.8.4