brw-7000-run-1

New build with 3090 and 7800X3D

HTML result view exported from: https://openbenchmarking.org/result/2307021-NE-BRW7000RU32&grw.

brw-7000-run-1ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNew Ryzen 7800X build ML suite testsAMD Ryzen 7 7800X3D 8-Core @ 4.20GHz (8 Cores / 16 Threads)ASUS ROG STRIX X670E-I GAMING WIFI (1616 BIOS)AMD Device 14d862GB2 x 4001GB Western Digital WD_BLACK SN850X 4000GB + 8002GB Samsung SSD 870 + 128GB Flash Drive FITNVIDIA GeForce RTX 3090 24GBNVIDIA GA102 HD AudioHP Z27Intel I225-V + MEDIATEK Device 0616Ubuntu 22.045.19.0-46-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.4NVIDIA 530.30.024.6.0OpenCL 3.0 CUDA 12.1.681.3.236GCC 11.3.0 + CUDA 12.1ext43840x2160OpenBenchmarking.org- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-aYxV0E/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-aYxV0E/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa601203- GLAMOR - BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.02.32.00.02- GPU Compute Cores: 10496- Python 3.10.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

brw-7000-run-1tensorflow: CPU - 16 - VGG-16tensorflow: CPU - 32 - VGG-16tensorflow: CPU - 64 - VGG-16tensorflow: CPU - 16 - AlexNettensorflow: CPU - 256 - VGG-16tensorflow: CPU - 32 - AlexNettensorflow: CPU - 512 - VGG-16tensorflow: CPU - 64 - AlexNettensorflow: CPU - 256 - AlexNettensorflow: CPU - 512 - AlexNettensorflow: CPU - 16 - GoogLeNettensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 32 - GoogLeNettensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 64 - GoogLeNettensorflow: CPU - 64 - ResNet-50tensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNettensorflow: CPU - 512 - ResNet-50numenta-nab: KNN CADnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Contextual Anomaly Detector OSErbenchmark: numpy: deepspeech: CPUrnnoise: mnn: nasnetmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3opencv: DNN - Deep Neural Networktensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2tnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1caffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200caffe: AlexNet - CPU - 1000caffe: GoogleNet - CPU - 100caffe: GoogleNet - CPU - 200caffe: GoogleNet - CPU - 1000shoc: OpenCL - S3Dshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Reductionshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthncnn: 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 - 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 - FastestDetncnn: Vulkan GPU - mnasnetmlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressiononednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - 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: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUNew Ryzen 7800X build ML suite tests10.6411.0111.19134.6711.31176.8511.35207.73229.27232.40104.3333.87100.5333.4096.1732.6292.6631.5792.4131.34157.93911.7116.05273.25126.14030.2880.0881794.5139.5395414.7936.4440.8201.3967.6982.6661.9531.75316.712213831712.6125246.84955.641181.092650.9023232.12389.930199.48746.282194.929232734630223065664281128414642171428.06925.73532350.9243.0550388.0227921.3039184.326.892127.12272172.476.481.961.591.691.742.660.664.7320.834.553.419.6110.228.065.33107.542.132.721.301.841.233.130.724.434.071.630.972.395.7123.411.60143.151.861.0129.2821.9814.141.443.409543.138440.6415980.3811501.293641.321505.121855.634114.181714.650560.8542341.034952309.941170.332313.322.133637.373092.515821164.872429.391415.44OpenBenchmarking.org

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: VGG-16New Ryzen 7800X build ML suite tests3691215SE +/- 0.01, N = 310.64

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16New Ryzen 7800X build ML suite tests3691215SE +/- 0.00, N = 311.01

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16New Ryzen 7800X build ML suite tests3691215SE +/- 0.00, N = 311.19

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetNew Ryzen 7800X build ML suite tests306090120150SE +/- 0.05, N = 3134.67

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: VGG-16New Ryzen 7800X build ML suite tests3691215SE +/- 0.00, N = 311.31

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetNew Ryzen 7800X build ML suite tests4080120160200SE +/- 0.43, N = 3176.85

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: VGG-16New Ryzen 7800X build ML suite tests3691215SE +/- 0.00, N = 311.35

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetNew Ryzen 7800X build ML suite tests50100150200250SE +/- 0.09, N = 3207.73

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetNew Ryzen 7800X build ML suite tests50100150200250SE +/- 0.11, N = 3229.27

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetNew Ryzen 7800X build ML suite tests50100150200250SE +/- 0.18, N = 3232.40

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.04, N = 3104.33

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50New Ryzen 7800X build ML suite tests816243240SE +/- 0.01, N = 333.87

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.10, N = 3100.53

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50New Ryzen 7800X build ML suite tests816243240SE +/- 0.01, N = 333.40

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.01, N = 396.17

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50New Ryzen 7800X build ML suite tests816243240SE +/- 0.01, N = 332.62

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.02, N = 392.66

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50New Ryzen 7800X build ML suite tests714212835SE +/- 0.01, N = 331.57

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.01, N = 392.41

TensorFlow

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

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50New Ryzen 7800X build ML suite tests714212835SE +/- 0.01, N = 331.34

Numenta Anomaly Benchmark

Detector: KNN CAD

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADNew Ryzen 7800X build ML suite tests306090120150SE +/- 0.35, N = 3157.94

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyNew Ryzen 7800X build ML suite tests3691215SE +/- 0.09, N = 311.71

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianNew Ryzen 7800X build ML suite tests246810SE +/- 0.019, N = 36.052

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineNew Ryzen 7800X build ML suite tests1632486480SE +/- 0.65, N = 1573.25

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointNew Ryzen 7800X build ML suite tests612182430SE +/- 0.09, N = 326.14

Numenta Anomaly Benchmark

Detector: Contextual Anomaly Detector OSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSENew Ryzen 7800X build ML suite tests714212835SE +/- 0.18, N = 330.29

R Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkNew Ryzen 7800X build ML suite tests0.01980.03960.05940.07920.099SE +/- 0.0003, N = 30.08811. R scripting front-end version 4.1.2 (2021-11-01)

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkNew Ryzen 7800X build ML suite tests2004006008001000SE +/- 2.20, N = 3794.51

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUNew Ryzen 7800X build ML suite tests918273645SE +/- 0.08, N = 339.54

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28New Ryzen 7800X build ML suite tests48121620SE +/- 0.02, N = 314.791. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

Mobile Neural Network

Model: nasnet

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetNew Ryzen 7800X build ML suite tests246810SE +/- 0.108, N = 156.444MIN: 5.89 / MAX: 35.361. (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: mobilenetV3New Ryzen 7800X build ML suite tests0.18450.3690.55350.7380.9225SE +/- 0.005, N = 150.820MIN: 0.77 / MAX: 9.911. (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: squeezenetv1.1New Ryzen 7800X build ML suite tests0.31410.62820.94231.25641.5705SE +/- 0.008, N = 151.396MIN: 1.32 / MAX: 9.081. (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-v2-50New Ryzen 7800X build ML suite tests246810SE +/- 0.043, N = 157.698MIN: 7.26 / MAX: 39.351. (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: SqueezeNetV1.0New Ryzen 7800X build ML suite tests0.59991.19981.79972.39962.9995SE +/- 0.020, N = 152.666MIN: 2.53 / MAX: 50.771. (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_224New Ryzen 7800X build ML suite tests0.43940.87881.31821.75762.197SE +/- 0.015, N = 151.953MIN: 1.83 / MAX: 29.371. (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: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0New Ryzen 7800X build ML suite tests0.39440.78881.18321.57761.972SE +/- 0.002, N = 151.753MIN: 1.68 / MAX: 8.821. (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-v3New Ryzen 7800X build ML suite tests48121620SE +/- 0.27, N = 1516.71MIN: 15.16 / MAX: 55.091. (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

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.7Test: DNN - Deep Neural NetworkNew Ryzen 7800X build ML suite tests5K10K15K20K25KSE +/- 397.13, N = 15213831. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetNew Ryzen 7800X build ML suite tests400800120016002000SE +/- 1.61, N = 31712.61

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4New Ryzen 7800X build ML suite tests5K10K15K20K25KSE +/- 10.75, N = 325246.8

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileNew Ryzen 7800X build ML suite tests11002200330044005500SE +/- 32.90, N = 34955.64

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatNew Ryzen 7800X build ML suite tests30060090012001500SE +/- 3.12, N = 31181.09

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantNew Ryzen 7800X build ML suite tests6001200180024003000SE +/- 6.49, N = 32650.90

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2New Ryzen 7800X build ML suite tests5K10K15K20K25KSE +/- 48.53, N = 323232.1

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 2.68, N = 32389.93MIN: 2332.55 / MAX: 2434.131. (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 v2New Ryzen 7800X build ML suite tests4080120160200SE +/- 0.50, N = 3199.49MIN: 195.78 / MAX: 206.361. (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 v2New Ryzen 7800X build ML suite tests1020304050SE +/- 0.53, N = 346.28MIN: 45 / MAX: 47.351. (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 v1.1New Ryzen 7800X build ML suite tests4080120160200SE +/- 0.06, N = 3194.93MIN: 194.02 / MAX: 195.681. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100New Ryzen 7800X build ML suite tests5K10K15K20K25KSE +/- 6.94, N = 3232731. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -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: 200New Ryzen 7800X build ML suite tests10K20K30K40K50KSE +/- 79.10, N = 3463021. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -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: 1000New Ryzen 7800X build ML suite tests50K100K150K200K250KSE +/- 183.04, N = 32306561. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -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: 100New Ryzen 7800X build ML suite tests14K28K42K56K70KSE +/- 102.96, N = 3642811. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -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: 200New Ryzen 7800X build ML suite tests30K60K90K120K150KSE +/- 216.53, N = 31284141. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -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: 1000New Ryzen 7800X build ML suite tests140K280K420K560K700KSE +/- 408.49, N = 36421711. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DNew Ryzen 7800X build ML suite tests90180270360450SE +/- 1.22, N = 3428.071. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadNew Ryzen 7800X build ML suite tests612182430SE +/- 0.01, N = 325.741. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 3.38, N = 32350.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashNew Ryzen 7800X build ML suite tests1020304050SE +/- 0.36, N = 343.061. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Reduction

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionNew Ryzen 7800X build ML suite tests80160240320400SE +/- 2.93, N = 10388.021. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: GEMM SGEMM_N

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NNew Ryzen 7800X build ML suite tests2K4K6K8K10KSE +/- 39.58, N = 37921.301. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsNew Ryzen 7800X build ML suite tests8K16K24K32K40KSE +/- 228.09, N = 339184.31. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadNew Ryzen 7800X build ML suite tests612182430SE +/- 0.00, N = 326.891. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackNew Ryzen 7800X build ML suite tests612182430SE +/- 0.00, N = 327.121. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 3.16, N = 32172.471. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetNew Ryzen 7800X build ML suite tests246810SE +/- 0.09, N = 156.48MIN: 5.85 / MAX: 13.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2New Ryzen 7800X build ML suite tests0.4410.8821.3231.7642.205SE +/- 0.00, N = 151.96MIN: 1.88 / MAX: 9.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3New Ryzen 7800X build ML suite tests0.35780.71561.07341.43121.789SE +/- 0.00, N = 151.59MIN: 1.52 / MAX: 7.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2New Ryzen 7800X build ML suite tests0.38030.76061.14091.52121.9015SE +/- 0.01, N = 151.69MIN: 1.59 / MAX: 7.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetNew Ryzen 7800X build ML suite tests0.39150.7831.17451.5661.9575SE +/- 0.02, N = 141.74MIN: 1.63 / MAX: 6.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0New Ryzen 7800X build ML suite tests0.59851.1971.79552.3942.9925SE +/- 0.03, N = 152.66MIN: 2.47 / MAX: 10.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceNew Ryzen 7800X build ML suite tests0.14850.2970.44550.5940.7425SE +/- 0.01, N = 150.66MIN: 0.61 / MAX: 6.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetNew Ryzen 7800X build ML suite tests1.06432.12863.19294.25725.3215SE +/- 0.11, N = 154.73MIN: 4.19 / MAX: 11.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16New Ryzen 7800X build ML suite tests510152025SE +/- 0.21, N = 1520.83MIN: 19.11 / MAX: 67.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18New Ryzen 7800X build ML suite tests1.02382.04763.07144.09525.119SE +/- 0.08, N = 154.55MIN: 4.12 / MAX: 12.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetNew Ryzen 7800X build ML suite tests0.76731.53462.30193.06923.8365SE +/- 0.07, N = 153.41MIN: 2.89 / MAX: 10.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50New Ryzen 7800X build ML suite tests3691215SE +/- 0.17, N = 159.61MIN: 8.54 / MAX: 17.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyNew Ryzen 7800X build ML suite tests3691215SE +/- 0.13, N = 1510.22MIN: 9.12 / MAX: 21.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdNew Ryzen 7800X build ML suite tests246810SE +/- 0.12, N = 158.06MIN: 7.11 / MAX: 16.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mNew Ryzen 7800X build ML suite tests1.19932.39863.59794.79725.9965SE +/- 0.01, N = 155.33MIN: 4.92 / MAX: 12.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerNew Ryzen 7800X build ML suite tests20406080100SE +/- 0.06, N = 15107.54MIN: 104.27 / MAX: 135.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetNew Ryzen 7800X build ML suite tests0.47930.95861.43791.91722.3965SE +/- 0.03, N = 152.13MIN: 1.9 / MAX: 7.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetNew Ryzen 7800X build ML suite tests0.6121.2241.8362.4483.06SE +/- 0.02, N = 32.72MIN: 2.52 / MAX: 9.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2New Ryzen 7800X build ML suite tests0.29250.5850.87751.171.4625SE +/- 0.15, N = 31.30MIN: 0.93 / MAX: 7.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3New Ryzen 7800X build ML suite tests0.4140.8281.2421.6562.07SE +/- 0.01, N = 31.84MIN: 1.22 / MAX: 7.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2New Ryzen 7800X build ML suite tests0.27680.55360.83041.10721.384SE +/- 0.01, N = 31.23MIN: 1.17 / MAX: 5.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0New Ryzen 7800X build ML suite tests0.70431.40862.11292.81723.5215SE +/- 0.56, N = 33.13MIN: 2.08 / MAX: 20.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceNew Ryzen 7800X build ML suite tests0.1620.3240.4860.6480.81SE +/- 0.01, N = 30.72MIN: 0.67 / MAX: 4.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetNew Ryzen 7800X build ML suite tests0.99681.99362.99043.98724.984SE +/- 0.10, N = 34.43MIN: 1.78 / MAX: 37.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16New Ryzen 7800X build ML suite tests0.91581.83162.74743.66324.579SE +/- 1.07, N = 34.07MIN: 1.41 / MAX: 33.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18New Ryzen 7800X build ML suite tests0.36680.73361.10041.46721.834SE +/- 0.03, N = 31.63MIN: 0.96 / MAX: 11.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetNew Ryzen 7800X build ML suite tests0.21830.43660.65490.87321.0915SE +/- 0.01, N = 30.97MIN: 0.91 / MAX: 6.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50New Ryzen 7800X build ML suite tests0.53781.07561.61342.15122.689SE +/- 0.04, N = 32.39MIN: 1.58 / MAX: 10.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyNew Ryzen 7800X build ML suite tests1.28482.56963.85445.13926.424SE +/- 0.08, N = 35.71MIN: 4.49 / MAX: 29.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdNew Ryzen 7800X build ML suite tests612182430SE +/- 0.20, N = 323.41MIN: 6.35 / MAX: 65.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mNew Ryzen 7800X build ML suite tests0.360.721.081.441.8SE +/- 0.01, N = 31.60MIN: 1.52 / MAX: 5.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerNew Ryzen 7800X build ML suite tests306090120150SE +/- 0.73, N = 3143.15MIN: 120.39 / MAX: 716.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetNew Ryzen 7800X build ML suite tests0.41850.8371.25551.6742.0925SE +/- 0.09, N = 31.86MIN: 1.31 / MAX: 6.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetNew Ryzen 7800X build ML suite tests0.22730.45460.68190.90921.1365SE +/- 0.01, N = 21.01MIN: 0.94 / MAX: 4.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaNew Ryzen 7800X build ML suite tests714212835SE +/- 0.06, N = 329.28

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaNew Ryzen 7800X build ML suite tests510152025SE +/- 0.03, N = 321.98

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmNew Ryzen 7800X build ML suite tests48121620SE +/- 0.00, N = 314.14

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionNew Ryzen 7800X build ML suite tests0.3240.6480.9721.2961.62SE +/- 0.02, N = 31.44

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.76711.53422.30133.06843.8355SE +/- 0.00926, N = 33.40954MIN: 3.151. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.70611.41222.11832.82443.5305SE +/- 0.01172, N = 33.13844MIN: 3.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.14440.28880.43320.57760.722SE +/- 0.002841, N = 30.641598MIN: 0.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.08580.17160.25740.34320.429SE +/- 0.001159, N = 30.381150MIN: 0.361. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests0.29110.58220.87331.16441.4555SE +/- 0.00064, N = 31.29364MIN: 1.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests0.29730.59460.89191.18921.4865SE +/- 0.00136, N = 31.32150MIN: 1.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests1.15242.30483.45724.60965.762SE +/- 0.00908, N = 35.12185MIN: 4.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests1.26772.53543.80315.07086.3385SE +/- 0.05918, N = 155.63411MIN: 4.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.94091.88182.82273.76364.7045SE +/- 0.00329, N = 34.18171MIN: 4.041. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests1.04642.09283.13924.18565.232SE +/- 0.02144, N = 34.65056MIN: 4.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.19220.38440.57660.76880.961SE +/- 0.002888, N = 30.854234MIN: 0.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests0.23290.46580.69870.93161.1645SE +/- 0.00177, N = 31.03495MIN: 0.991. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 2.34, N = 32309.94MIN: 2284.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUNew Ryzen 7800X build ML suite tests30060090012001500SE +/- 2.77, N = 31170.33MIN: 1147.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 2.36, N = 32313.32MIN: 2281.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests0.48010.96021.44031.92042.4005SE +/- 0.00749, N = 32.13363MIN: 2.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests246810SE +/- 0.04306, N = 37.37309MIN: 7.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests0.56611.13221.69832.26442.8305SE +/- 0.00431, N = 32.51582MIN: 2.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUNew Ryzen 7800X build ML suite tests30060090012001500SE +/- 1.27, N = 31164.87MIN: 1145.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests5001000150020002500SE +/- 55.34, N = 122429.39MIN: 2278.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.1Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUNew Ryzen 7800X build ML suite tests30060090012001500SE +/- 130.52, N = 151415.44MIN: 1146.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Phoronix Test Suite v10.8.5