10700t mid june Intel Core i7-10700T testing with a Logic Supply RXM-181 (Z01-0002A026 BIOS) and Intel UHD 630 CML GT2 3GB on Ubuntu 21.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2106215-IB-10700TMID26&grs&sor .
10700t mid june Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution 1 2 3 Intel Core i7-10700T @ 4.50GHz (8 Cores / 16 Threads) Logic Supply RXM-181 (Z01-0002A026 BIOS) Intel Comet Lake PCH 32GB 256GB TS256GMTS800 Intel UHD 630 CML GT2 3GB (1200MHz) Realtek ALC233 DELL P2415Q Intel I219-LM + Intel I210 Ubuntu 21.04 5.11.0-17-generic (x86_64) GNOME Shell 3.38.4 X Server + Wayland 4.6 Mesa 21.0.1 1.2.145 GCC 10.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe0 - Thermald 2.4.3 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + 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
10700t mid june ncnn: CPU - resnet18 ncnn: CPU - resnet50 ncnn: CPU - googlenet ncnn: CPU - mobilenet unvanquished: 1024 x 768 - Ultra mnn: resnet-v2-50 ncnn: CPU - squeezenet_ssd mnn: squeezenetv1.1 ncnn: CPU - yolov4-tiny mnn: mobilenet-v1-1.0 mnn: inception-v3 tnn: CPU - DenseNet unvanquished: 1024 x 768 - Medium mnn: SqueezeNetV1.0 unvanquished: 1280 x 1024 - Medium unvanquished: 800 x 600 - Ultra unvanquished: 800 x 600 - High tnn: CPU - MobileNet v2 mnn: mobilenetV3 unvanquished: 1920 x 1080 - Medium unvanquished: 1024 x 768 - High unvanquished: 1280 x 1024 - High ncnn: CPU - vgg16 tnn: CPU - SqueezeNet v2 unvanquished: 800 x 600 - Medium unvanquished: 1920 x 1080 - High unvanquished: 1280 x 1024 - Ultra unvanquished: 1920 x 1080 - Ultra ncnn: CPU - alexnet tnn: CPU - SqueezeNet v1.1 gravitymark: 1920 x 1080 - OpenGL ES gravitymark: 1920 x 1080 - OpenGL ncnn: CPU - regnety_400m ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 mnn: MobileNetV2_224 1 2 3 19.97 35.44 20.03 24.31 98.0 48.287 27.79 6.453 35.73 4.778 65.480 4271.255 216.9 10.222 206.4 137.7 213.8 380.967 3.107 164.3 207.9 172.0 72.88 83.041 226.6 121.0 69.4 51.4 16.66 359.799 9.3 0.6 13.78 2.36 9.22 5.57 5.25 5.46 5.81 4.240 19.95 36.65 20.04 24.62 98.7 48.410 28.35 6.527 36.38 4.805 66.315 4279.603 220.0 10.358 205.7 136.1 214.6 384.501 3.127 163.0 208.8 172.2 73.24 83.298 226.1 121.1 69.4 51.5 16.69 360.064 9.3 0.6 13.12 2.24 8.70 5.63 5.28 5.48 5.91 4.259 20.82 35.90 20.63 24.92 96.4 47.334 28.13 6.572 35.80 4.721 65.256 4212.975 219.9 10.248 208.3 137.3 216.1 380.432 3.132 163.7 209.5 173.1 73.21 82.926 227.1 121.4 69.2 51.5 16.67 359.500 9.3 0.6 13.85 2.36 8.84 5.45 5.57 5.48 6.05 4.219 OpenBenchmarking.org
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: resnet18 2 1 3 5 10 15 20 25 SE +/- 0.24, N = 3 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 19.95 19.97 20.82 MIN: 18.15 / MAX: 33.5 MIN: 18.43 / MAX: 31.3 MIN: 18.55 / MAX: 31.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: resnet50 1 3 2 8 16 24 32 40 SE +/- 0.14, N = 3 SE +/- 0.38, N = 3 SE +/- 0.04, N = 3 35.44 35.90 36.65 MIN: 33.12 / MAX: 45.76 MIN: 33.7 / MAX: 50.22 MIN: 34.66 / MAX: 50.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: googlenet 1 2 3 5 10 15 20 25 SE +/- 0.16, N = 3 SE +/- 0.66, N = 3 SE +/- 0.48, N = 3 20.03 20.04 20.63 MIN: 18.36 / MAX: 32.6 MIN: 15.33 / MAX: 33.65 MIN: 18.17 / MAX: 25.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: mobilenet 1 2 3 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 24.31 24.62 24.92 MIN: 23.18 / MAX: 36.4 MIN: 23.39 / MAX: 37.9 MIN: 23.62 / MAX: 37.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Unvanquished Resolution: 1024 x 768 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1024 x 768 - Effects Quality: Ultra 2 1 3 20 40 60 80 100 SE +/- 0.22, N = 3 SE +/- 0.44, N = 3 SE +/- 0.41, N = 3 98.7 98.0 96.4
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 3 1 2 11 22 33 44 55 SE +/- 0.26, N = 3 SE +/- 0.46, N = 3 SE +/- 0.67, N = 3 47.33 48.29 48.41 MIN: 43.26 / MAX: 66.93 MIN: 43.69 / MAX: 67.49 MIN: 43.12 / MAX: 66.35 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: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: squeezenet_ssd 1 3 2 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.55, N = 3 SE +/- 0.15, N = 3 27.79 28.13 28.35 MIN: 25.74 / MAX: 41.54 MIN: 25.75 / MAX: 37.92 MIN: 26.33 / MAX: 37.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 1 2 3 2 4 6 8 10 SE +/- 0.030, N = 3 SE +/- 0.034, N = 3 SE +/- 0.076, N = 3 6.453 6.527 6.572 MIN: 5.54 / MAX: 23.26 MIN: 5.75 / MAX: 23.61 MIN: 5.73 / MAX: 24.78 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: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: yolov4-tiny 1 3 2 8 16 24 32 40 SE +/- 0.53, N = 3 SE +/- 0.26, N = 3 SE +/- 0.19, N = 3 35.73 35.80 36.38 MIN: 33.7 / MAX: 46.45 MIN: 34.2 / MAX: 48.06 MIN: 34.8 / MAX: 48.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 3 1 2 1.0811 2.1622 3.2433 4.3244 5.4055 SE +/- 0.139, N = 3 SE +/- 0.140, N = 3 SE +/- 0.098, N = 3 4.721 4.778 4.805 MIN: 3.89 / MAX: 21.89 MIN: 3.86 / MAX: 23.71 MIN: 3.9 / MAX: 22.37 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 3 1 2 15 30 45 60 75 SE +/- 0.63, N = 3 SE +/- 0.81, N = 3 SE +/- 0.27, N = 3 65.26 65.48 66.32 MIN: 59.29 / MAX: 87.21 MIN: 59.87 / MAX: 109.47 MIN: 59.92 / MAX: 85.86 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
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet 3 1 2 900 1800 2700 3600 4500 SE +/- 11.71, N = 3 SE +/- 13.40, N = 3 SE +/- 5.82, N = 3 4212.98 4271.26 4279.60 MIN: 3926.66 / MAX: 4290.67 MIN: 4206.84 / MAX: 4358.97 MIN: 4019.16 / MAX: 4354.65 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Unvanquished Resolution: 1024 x 768 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1024 x 768 - Effects Quality: Medium 2 3 1 50 100 150 200 250 SE +/- 0.15, N = 3 SE +/- 1.01, N = 3 SE +/- 2.58, N = 3 220.0 219.9 216.9
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 1 3 2 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 10.22 10.25 10.36 MIN: 8.89 / MAX: 29.71 MIN: 8.7 / MAX: 29.05 MIN: 8.99 / MAX: 28.72 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
Unvanquished Resolution: 1280 x 1024 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1280 x 1024 - Effects Quality: Medium 3 1 2 50 100 150 200 250 SE +/- 1.20, N = 3 SE +/- 0.95, N = 3 SE +/- 1.66, N = 3 208.3 206.4 205.7
Unvanquished Resolution: 800 x 600 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 800 x 600 - Effects Quality: Ultra 1 3 2 30 60 90 120 150 SE +/- 1.30, N = 3 SE +/- 1.17, N = 15 SE +/- 1.55, N = 3 137.7 137.3 136.1
Unvanquished Resolution: 800 x 600 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 800 x 600 - Effects Quality: High 3 2 1 50 100 150 200 250 SE +/- 0.97, N = 3 SE +/- 1.87, N = 3 SE +/- 0.98, N = 3 216.1 214.6 213.8
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 3 1 2 80 160 240 320 400 SE +/- 0.57, N = 3 SE +/- 0.58, N = 3 SE +/- 1.58, N = 3 380.43 380.97 384.50 MIN: 378.4 / MAX: 384.99 MIN: 377.6 / MAX: 387.16 MIN: 380.16 / MAX: 391.73 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 1 2 3 0.7047 1.4094 2.1141 2.8188 3.5235 SE +/- 0.011, N = 3 SE +/- 0.013, N = 3 SE +/- 0.024, N = 3 3.107 3.127 3.132 MIN: 2.58 / MAX: 21.4 MIN: 2.6 / MAX: 21.44 MIN: 2.58 / MAX: 9.22 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
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Medium 1 3 2 40 80 120 160 200 SE +/- 0.98, N = 3 SE +/- 0.35, N = 3 SE +/- 0.78, N = 3 164.3 163.7 163.0
Unvanquished Resolution: 1024 x 768 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1024 x 768 - Effects Quality: High 3 2 1 50 100 150 200 250 SE +/- 0.61, N = 3 SE +/- 0.61, N = 3 SE +/- 1.56, N = 3 209.5 208.8 207.9
Unvanquished Resolution: 1280 x 1024 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1280 x 1024 - Effects Quality: High 3 2 1 40 80 120 160 200 SE +/- 0.32, N = 3 SE +/- 1.85, N = 3 SE +/- 1.78, N = 3 173.1 172.2 172.0
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: vgg16 1 3 2 16 32 48 64 80 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.25, N = 3 72.88 73.21 73.24 MIN: 71.06 / MAX: 84.38 MIN: 71.44 / MAX: 86.87 MIN: 71.35 / MAX: 86.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 3 1 2 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.24, N = 3 82.93 83.04 83.30 MIN: 82.77 / MAX: 88.64 MIN: 82.84 / MAX: 83.91 MIN: 82.87 / MAX: 89.37 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Unvanquished Resolution: 800 x 600 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 800 x 600 - Effects Quality: Medium 3 1 2 50 100 150 200 250 SE +/- 1.18, N = 3 SE +/- 0.35, N = 3 SE +/- 0.56, N = 3 227.1 226.6 226.1
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: High 3 2 1 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.54, N = 3 SE +/- 0.48, N = 3 121.4 121.1 121.0
Unvanquished Resolution: 1280 x 1024 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1280 x 1024 - Effects Quality: Ultra 2 1 3 15 30 45 60 75 SE +/- 0.12, N = 3 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 69.4 69.4 69.2
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 1920 x 1080 - Effects Quality: Ultra 3 2 1 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 51.5 51.5 51.4
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: alexnet 1 3 2 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 16.66 16.67 16.69 MIN: 15 / MAX: 30.02 MIN: 15.41 / MAX: 29.97 MIN: 15.16 / MAX: 29.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 3 1 2 80 160 240 320 400 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 359.50 359.80 360.06 MIN: 359.04 / MAX: 360.36 MIN: 359.06 / MAX: 360.67 MIN: 359.56 / MAX: 363.71 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
GravityMark Resolution: 1920 x 1080 - Renderer: OpenGL ES OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1080 - Renderer: OpenGL ES 3 2 1 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 9.3 9.3 9.3
GravityMark Resolution: 1920 x 1080 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1080 - Renderer: OpenGL 3 2 1 0.135 0.27 0.405 0.54 0.675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.6 0.6 0.6
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: regnety_400m 2 1 3 4 8 12 16 20 SE +/- 0.83, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 13.12 13.78 13.85 MIN: 10.75 / MAX: 26.65 MIN: 12.63 / MAX: 24.8 MIN: 12.63 / MAX: 26.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: blazeface 2 1 3 0.531 1.062 1.593 2.124 2.655 SE +/- 0.18, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 2.24 2.36 2.36 MIN: 1.81 / MAX: 13.51 MIN: 2.12 / MAX: 6.12 MIN: 2.11 / MAX: 3.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: efficientnet-b0 2 3 1 3 6 9 12 15 SE +/- 0.59, N = 3 SE +/- 0.32, N = 3 SE +/- 0.02, N = 3 8.70 8.84 9.22 MIN: 6.96 / MAX: 10.61 MIN: 7.15 / MAX: 10.47 MIN: 8.25 / MAX: 21.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: mnasnet 3 1 2 1.2668 2.5336 3.8004 5.0672 6.334 SE +/- 0.54, N = 2 SE +/- 0.41, N = 3 SE +/- 0.43, N = 3 5.45 5.57 5.63 MIN: 4.54 / MAX: 10.03 MIN: 4.36 / MAX: 8.31 MIN: 4.43 / MAX: 17.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: shufflenet-v2 1 2 3 1.2533 2.5066 3.7599 5.0132 6.2665 SE +/- 0.34, N = 3 SE +/- 0.36, N = 3 SE +/- 0.42, N = 3 5.25 5.28 5.57 MIN: 4.26 / MAX: 7.13 MIN: 4.24 / MAX: 7.04 MIN: 4.42 / MAX: 16.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU-v3-v3 - Model: mobilenet-v3 1 2 3 1.233 2.466 3.699 4.932 6.165 SE +/- 0.37, N = 3 SE +/- 0.39, N = 3 SE +/- 0.32, N = 3 5.46 5.48 5.48 MIN: 4.37 / MAX: 7.21 MIN: 4.35 / MAX: 7.31 MIN: 4.47 / MAX: 7.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU-v2-v2 - Model: mobilenet-v2 1 2 3 2 4 6 8 10 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.23, N = 3 5.81 5.91 6.05 MIN: 5.21 / MAX: 7.89 MIN: 5.27 / MAX: 7.63 MIN: 5.26 / MAX: 28.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 3 1 2 0.9583 1.9166 2.8749 3.8332 4.7915 SE +/- 0.335, N = 3 SE +/- 0.360, N = 3 SE +/- 0.380, N = 3 4.219 4.240 4.259 MIN: 3.1 / MAX: 23.03 MIN: 3.08 / MAX: 25.55 MIN: 3.06 / MAX: 16.02 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
Phoronix Test Suite v10.8.4