jul-27 AMD Ryzen 5 5600X 6-Core testing with a MSI MAG B550M MORTAR (MS-7C94) v1.0 (1.B3 BIOS) and AMD Radeon RX 570 4GB on Linuxmint 20.3 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2207254-NE-JUL27256197 .
jul-27 Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution first run of mach learning AMD Ryzen 5 5600X 6-Core @ 3.70GHz (6 Cores / 12 Threads) MSI MAG B550M MORTAR (MS-7C94) v1.0 (1.B3 BIOS) AMD Starship/Matisse 16GB 500GB Western Digital WDBRPG5000ANC-WRSN AMD Radeon RX 570 4GB (1250/1750MHz) AMD Ellesmere HDMI Audio Realtek RTL8125 2.5GbE Linuxmint 20.3 5.15.0-41-generic (x86_64) Cinnamon 5.2.7 X Server 1.20.13 4.6 Mesa 21.2.6 (LLVM 12.0.0) 1.2.182 GCC 9.4.0 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-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 - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201016 - GLAMOR - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0003400_100 - Python 3.8.10 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
jul-27 lczero: BLAS onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU numpy: deepspeech: CPU rnnoise: tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m tnn: CPU - DenseNet tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v2 tnn: CPU - SqueezeNet v1.1 plaidml: No - Inference - VGG16 - CPU plaidml: No - Inference - ResNet 50 - CPU numenta-nab: EXPoSE numenta-nab: Relative Entropy numenta-nab: Windowed Gaussian numenta-nab: Earthgecko Skyline numenta-nab: Bayesian Changepoint ai-benchmark: Device Inference Score ai-benchmark: Device Training Score ai-benchmark: Device AI Score mlpack: scikit_ica mlpack: scikit_qda mlpack: scikit_svm mlpack: scikit_linearridgeregression scikit-learn: opencv: DNN - Deep Neural Network first run of mach learning 582 4.27799 10.6634 1.75566 1.86109 19.6952 7.55966 8.02806 17.3158 2.53936 4.22548 3929.63 2250.82 3922.51 2248.96 2.62574 3931.53 2255.01 1.14671 536.70 50.74682 15.879 3667.24 53104.7 8869.88 2643.59 4429.29 48694.2 1.264 2.506 23.646 3.751 2.085 2.991 26.428 13.33 3.13 2.68 2.63 2.82 4.26 1.20 12.27 57.84 14.60 13.15 23.36 21.40 17.07 6.68 6.82 3.43 5.06 2.97 3.77 16.90 1.30 7.37 16.97 3.34 6.37 9.37 8.53 7.14 8.16 2687.858 229.937 50.093 217.406 11.20 9.65 561.042 22.654 14.064 128.061 37.878 1042 1056 2098 53.28 66.53 16.86 4.62 8.331 10461 OpenBenchmarking.org
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS first run of mach learning 130 260 390 520 650 SE +/- 5.78, N = 3 582 1. (CXX) g++ options: -flto -pthread
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU first run of mach learning 0.9625 1.925 2.8875 3.85 4.8125 SE +/- 0.01012, N = 3 4.27799 MIN: 4.08 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU first run of mach learning 3 6 9 12 15 SE +/- 0.02, N = 3 10.66 MIN: 10.49 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU first run of mach learning 0.395 0.79 1.185 1.58 1.975 SE +/- 0.00074, N = 3 1.75566 MIN: 1.66 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU first run of mach learning 0.4187 0.8374 1.2561 1.6748 2.0935 SE +/- 0.00299, N = 3 1.86109 MIN: 1.75 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU first run of mach learning 5 10 15 20 25 SE +/- 0.01, N = 3 19.70 MIN: 18.83 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU first run of mach learning 2 4 6 8 10 SE +/- 0.02456, N = 3 7.55966 MIN: 7.02 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU first run of mach learning 2 4 6 8 10 SE +/- 0.01961, N = 3 8.02806 MIN: 7.84 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU first run of mach learning 4 8 12 16 20 SE +/- 0.15, N = 15 17.32 MIN: 15.38 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU first run of mach learning 0.5714 1.1428 1.7142 2.2856 2.857 SE +/- 0.00243, N = 3 2.53936 MIN: 2.38 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU first run of mach learning 0.9507 1.9014 2.8521 3.8028 4.7535 SE +/- 0.01117, N = 3 4.22548 MIN: 3.93 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU first run of mach learning 800 1600 2400 3200 4000 SE +/- 7.56, N = 3 3929.63 MIN: 3892.98 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU first run of mach learning 500 1000 1500 2000 2500 SE +/- 4.02, N = 3 2250.82 MIN: 2231.06 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU first run of mach learning 800 1600 2400 3200 4000 SE +/- 2.72, N = 3 3922.51 MIN: 3907.55 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU first run of mach learning 500 1000 1500 2000 2500 SE +/- 3.07, N = 3 2248.96 MIN: 2230.7 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU first run of mach learning 0.5908 1.1816 1.7724 2.3632 2.954 SE +/- 0.00267, N = 3 2.62574 MIN: 2.51 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU first run of mach learning 800 1600 2400 3200 4000 SE +/- 2.67, N = 3 3931.53 MIN: 3915.53 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU first run of mach learning 500 1000 1500 2000 2500 SE +/- 2.14, N = 3 2255.01 MIN: 2239.26 1. (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.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU first run of mach learning 0.258 0.516 0.774 1.032 1.29 SE +/- 0.00222, N = 3 1.14671 MIN: 1.05 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark first run of mach learning 120 240 360 480 600 SE +/- 0.61, N = 3 536.70
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU first run of mach learning 11 22 33 44 55 SE +/- 0.05, N = 3 50.75
RNNoise OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 first run of mach learning 4 8 12 16 20 SE +/- 0.05, N = 3 15.88 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet first run of mach learning 800 1600 2400 3200 4000 SE +/- 14.21, N = 3 3667.24
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 first run of mach learning 11K 22K 33K 44K 55K SE +/- 100.52, N = 3 53104.7
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile first run of mach learning 2K 4K 6K 8K 10K SE +/- 22.90, N = 3 8869.88
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float first run of mach learning 600 1200 1800 2400 3000 SE +/- 6.33, N = 3 2643.59
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant first run of mach learning 900 1800 2700 3600 4500 SE +/- 15.00, N = 3 4429.29
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 first run of mach learning 10K 20K 30K 40K 50K SE +/- 147.62, N = 3 48694.2
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 first run of mach learning 0.2844 0.5688 0.8532 1.1376 1.422 SE +/- 0.001, N = 3 1.264 MIN: 1.24 / MAX: 1.85 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 first run of mach learning 0.5639 1.1278 1.6917 2.2556 2.8195 SE +/- 0.005, N = 3 2.506 MIN: 2.45 / MAX: 3.83 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 first run of mach learning 6 12 18 24 30 SE +/- 0.06, N = 3 23.65 MIN: 23.13 / MAX: 34.32 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 first run of mach learning 0.844 1.688 2.532 3.376 4.22 SE +/- 0.022, N = 3 3.751 MIN: 3.62 / MAX: 5.2 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 first run of mach learning 0.4691 0.9382 1.4073 1.8764 2.3455 SE +/- 0.025, N = 3 2.085 MIN: 2.02 / MAX: 4.19 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 first run of mach learning 0.673 1.346 2.019 2.692 3.365 SE +/- 0.018, N = 3 2.991 MIN: 2.89 / MAX: 20.77 1. (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.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 first run of mach learning 6 12 18 24 30 SE +/- 0.10, N = 3 26.43 MIN: 25.82 / MAX: 47.06 1. (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.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet first run of mach learning 3 6 9 12 15 SE +/- 0.13, N = 6 13.33 MIN: 12.86 / MAX: 14.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 first run of mach learning 0.7043 1.4086 2.1129 2.8172 3.5215 SE +/- 0.07, N = 6 3.13 MIN: 2.82 / MAX: 4.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 first run of mach learning 0.603 1.206 1.809 2.412 3.015 SE +/- 0.02, N = 6 2.68 MIN: 2.55 / MAX: 3.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 first run of mach learning 0.5918 1.1836 1.7754 2.3672 2.959 SE +/- 0.02, N = 6 2.63 MIN: 2.49 / MAX: 3.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet first run of mach learning 0.6345 1.269 1.9035 2.538 3.1725 SE +/- 0.03, N = 6 2.82 MIN: 2.58 / MAX: 4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 first run of mach learning 0.9585 1.917 2.8755 3.834 4.7925 SE +/- 0.05, N = 6 4.26 MIN: 3.98 / MAX: 5.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface first run of mach learning 0.27 0.54 0.81 1.08 1.35 SE +/- 0.02, N = 6 1.20 MIN: 1.12 / MAX: 1.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet first run of mach learning 3 6 9 12 15 SE +/- 0.12, N = 6 12.27 MIN: 11.51 / MAX: 17.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 first run of mach learning 13 26 39 52 65 SE +/- 0.17, N = 6 57.84 MIN: 56.12 / MAX: 62.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 first run of mach learning 4 8 12 16 20 SE +/- 0.04, N = 6 14.60 MIN: 13.69 / MAX: 15.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet first run of mach learning 3 6 9 12 15 SE +/- 0.12, N = 6 13.15 MIN: 12.47 / MAX: 20.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 first run of mach learning 6 12 18 24 30 SE +/- 0.10, N = 6 23.36 MIN: 22.53 / MAX: 25.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny first run of mach learning 5 10 15 20 25 SE +/- 0.14, N = 6 21.40 MIN: 20.26 / MAX: 33.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd first run of mach learning 4 8 12 16 20 SE +/- 0.07, N = 6 17.07 MIN: 16.53 / MAX: 22.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m first run of mach learning 2 4 6 8 10 SE +/- 0.02, N = 6 6.68 MIN: 6.52 / MAX: 13.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet first run of mach learning 2 4 6 8 10 SE +/- 0.01, N = 3 6.82 MIN: 6.43 / MAX: 9.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 first run of mach learning 0.7718 1.5436 2.3154 3.0872 3.859 SE +/- 0.03, N = 3 3.43 MIN: 3.37 / MAX: 4.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 first run of mach learning 1.1385 2.277 3.4155 4.554 5.6925 SE +/- 0.05, N = 3 5.06 MIN: 4.38 / MAX: 9.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 first run of mach learning 0.6683 1.3366 2.0049 2.6732 3.3415 SE +/- 0.03, N = 3 2.97 MIN: 2.68 / MAX: 6.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet first run of mach learning 0.8483 1.6966 2.5449 3.3932 4.2415 SE +/- 0.01, N = 3 3.77 MIN: 3.57 / MAX: 5.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 first run of mach learning 4 8 12 16 20 SE +/- 0.24, N = 3 16.90 MIN: 11.28 / MAX: 19.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface first run of mach learning 0.2925 0.585 0.8775 1.17 1.4625 SE +/- 0.01, N = 3 1.30 MIN: 1.22 / MAX: 1.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet first run of mach learning 2 4 6 8 10 SE +/- 0.01, N = 3 7.37 MIN: 7.27 / MAX: 11.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 first run of mach learning 4 8 12 16 20 SE +/- 0.03, N = 3 16.97 MIN: 16.59 / MAX: 22.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 first run of mach learning 0.7515 1.503 2.2545 3.006 3.7575 SE +/- 0.00, N = 3 3.34 MIN: 3.18 / MAX: 3.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet first run of mach learning 2 4 6 8 10 SE +/- 0.00, N = 3 6.37 MIN: 5.98 / MAX: 6.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 first run of mach learning 3 6 9 12 15 SE +/- 0.00, N = 3 9.37 MIN: 8.69 / MAX: 9.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny first run of mach learning 2 4 6 8 10 SE +/- 0.01, N = 3 8.53 MIN: 8.46 / MAX: 16.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd first run of mach learning 2 4 6 8 10 SE +/- 0.01, N = 3 7.14 MIN: 6.72 / MAX: 7.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m first run of mach learning 2 4 6 8 10 SE +/- 0.01, N = 3 8.16 MIN: 8.04 / MAX: 10.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet first run of mach learning 600 1200 1800 2400 3000 SE +/- 11.44, N = 3 2687.86 MIN: 2642.22 / MAX: 2736.77 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 first run of mach learning 50 100 150 200 250 SE +/- 0.38, N = 3 229.94 MIN: 225.24 / MAX: 232.79 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 first run of mach learning 11 22 33 44 55 SE +/- 0.41, N = 3 50.09 MIN: 49.15 / MAX: 50.89 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 first run of mach learning 50 100 150 200 250 SE +/- 0.08, N = 3 217.41 MIN: 217.11 / MAX: 217.98 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU first run of mach learning 3 6 9 12 15 SE +/- 0.05, N = 3 11.20
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU first run of mach learning 3 6 9 12 15 SE +/- 0.04, N = 3 9.65
Numenta Anomaly Benchmark Detector: EXPoSE OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: EXPoSE first run of mach learning 120 240 360 480 600 SE +/- 1.38, N = 3 561.04
Numenta Anomaly Benchmark Detector: Relative Entropy OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy first run of mach learning 5 10 15 20 25 SE +/- 0.12, N = 3 22.65
Numenta Anomaly Benchmark Detector: Windowed Gaussian OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian first run of mach learning 4 8 12 16 20 SE +/- 0.05, N = 3 14.06
Numenta Anomaly Benchmark Detector: Earthgecko Skyline OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline first run of mach learning 30 60 90 120 150 SE +/- 0.50, N = 3 128.06
Numenta Anomaly Benchmark Detector: Bayesian Changepoint OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint first run of mach learning 9 18 27 36 45 SE +/- 0.17, N = 3 37.88
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score first run of mach learning 200 400 600 800 1000 1042
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score first run of mach learning 200 400 600 800 1000 1056
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score first run of mach learning 500 1000 1500 2000 2500 2098
Mlpack Benchmark Benchmark: scikit_ica OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica first run of mach learning 12 24 36 48 60 SE +/- 0.22, N = 3 53.28
Mlpack Benchmark Benchmark: scikit_qda OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda first run of mach learning 15 30 45 60 75 SE +/- 0.11, N = 3 66.53
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm first run of mach learning 4 8 12 16 20 SE +/- 0.02, N = 3 16.86
Mlpack Benchmark Benchmark: scikit_linearridgeregression OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression first run of mach learning 1.0395 2.079 3.1185 4.158 5.1975 SE +/- 0.03, N = 3 4.62
Scikit-Learn OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.22.1 first run of mach learning 2 4 6 8 10 SE +/- 0.031, N = 3 8.331
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.6 Test: DNN - Deep Neural Network first run of mach learning 2K 4K 6K 8K 10K SE +/- 109.46, N = 4 10461 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
Phoronix Test Suite v10.8.4