nn gravity 5950X AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3302 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Ubuntu 21.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2106192-IB-NNGRAVITY71&rdt&grs .
nn gravity 5950X Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution 1 2 3 4 AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3302 BIOS) AMD Starship/Matisse 32GB 500GB Western Digital WDS500G3X0C-00SJG0 AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz) AMD Navi 10 HDMI Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 21.04 5.11.0-18-generic (x86_64) GNOME Shell 3.38.4 X Server + Wayland 4.6 Mesa 21.0.1 (LLVM 11.0.1) 1.2.145 GCC 10.3.0 ext4 3840x2160 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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
nn gravity 5950X mnn: mobilenet-v1-1.0 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd mnn: resnet-v2-50 ncnn: CPU - mobilenet mnn: squeezenetv1.1 mnn: SqueezeNetV1.0 ncnn: CPU - resnet18 mnn: MobileNetV2_224 mnn: mobilenetV3 tnn: CPU - SqueezeNet v2 mnn: inception-v3 ncnn: CPU - efficientnet-b0 ncnn: CPU - resnet50 ncnn: CPU - alexnet gravitymark: 3840 x 2160 - OpenGL tnn: CPU - SqueezeNet v1.1 ncnn: CPU - mnasnet gravitymark: 1920 x 1080 - OpenGL ncnn: CPU - blazeface gravitymark: 1920 x 1200 - OpenGL ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - regnety_400m gravitymark: 2560 x 1440 - OpenGL tnn: CPU - MobileNet v2 ncnn: CPU - shufflenet-v2 gravitymark: 2560 x 1440 - Vulkan ncnn: CPU-v3-v3 - mobilenet-v3 gravitymark: 1920 x 1080 - Vulkan gravitymark: 1920 x 1200 - Vulkan ncnn: CPU - vgg16 tnn: CPU - DenseNet gravitymark: 3840 x 2160 - Vulkan ncnn: CPU - googlenet 1 2 3 4 2.735 23.96 15.69 23.535 12.98 4.454 5.467 15.52 3.639 2.162 51.177 27.737 5.44 25.85 12.13 60.3 211.659 3.92 93.7 1.81 93.2 4.34 9.96 81.4 225.073 4.15 83.9 4.15 93.6 94.4 60.21 2400.991 63.6 14.22 2.673 23.39 15.61 23.188 12.73 4.425 5.605 15.13 3.613 2.132 51.646 28.037 5.34 25.59 11.91 60.9 212.993 3.93 93.8 1.79 93.5 4.37 9.94 81.6 223.855 4.16 83.7 4.13 93.8 94.0 60.40 2402.099 63.5 13.68 2.613 23.09 15.55 23.094 12.59 4.430 5.613 15.44 3.548 2.110 50.548 27.943 5.36 25.38 12.05 60.6 210.134 3.96 94.3 1.81 92.7 4.35 10.03 81.6 223.155 4.15 83.9 4.15 93.9 94.1 60.20 2396.494 63.6 14.04 2.654 22.91 15.13 22.735 12.60 4.325 5.475 15.31 3.579 2.120 51.705 27.491 5.39 25.38 12.07 59.9 213.410 3.98 94.8 1.81 93.7 4.33 10.00 82.1 223.913 4.18 83.3 4.15 94.0 94.1 60.24 2402.680 63.6 13.78 OpenBenchmarking.org
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 1 2 3 4 0.6154 1.2308 1.8462 2.4616 3.077 SE +/- 0.043, N = 3 SE +/- 0.021, N = 8 SE +/- 0.029, N = 3 SE +/- 0.019, N = 3 2.735 2.673 2.613 2.654 MIN: 2.59 / MAX: 3.52 MIN: 2.49 / MAX: 11.38 MIN: 2.48 / MAX: 11.22 MIN: 2.54 / MAX: 3.34 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 2 3 4 6 12 18 24 30 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.04, N = 3 SE +/- 0.29, N = 4 23.96 23.39 23.09 22.91 MIN: 21.75 / MAX: 26.72 MIN: 21.61 / MAX: 102.02 MIN: 21.77 / MAX: 30.9 MIN: 21.2 / MAX: 31.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: squeezenet_ssd 1 2 3 4 4 8 12 16 20 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.21, N = 4 15.69 15.61 15.55 15.13 MIN: 14.8 / MAX: 17 MIN: 14.82 / MAX: 24.94 MIN: 14.74 / MAX: 16.92 MIN: 14.03 / MAX: 24.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 1 2 3 4 6 12 18 24 30 SE +/- 0.14, N = 3 SE +/- 0.17, N = 8 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 23.54 23.19 23.09 22.74 MIN: 22.51 / MAX: 34.52 MIN: 21.62 / MAX: 34.11 MIN: 21.99 / MAX: 33.51 MIN: 21.81 / MAX: 33.05 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 20210525 Target: CPU - Model: mobilenet 1 2 3 4 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 4 12.98 12.73 12.59 12.60 MIN: 12.02 / MAX: 45.58 MIN: 11.88 / MAX: 21.2 MIN: 11.76 / MAX: 13.68 MIN: 11.66 / MAX: 13.89 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 4 1.0022 2.0044 3.0066 4.0088 5.011 SE +/- 0.006, N = 3 SE +/- 0.058, N = 8 SE +/- 0.022, N = 3 SE +/- 0.081, N = 3 4.454 4.425 4.430 4.325 MIN: 4.2 / MAX: 13.68 MIN: 3.95 / MAX: 13.7 MIN: 4.19 / MAX: 13.77 MIN: 4.06 / MAX: 13.14 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 1 2 3 4 1.2629 2.5258 3.7887 5.0516 6.3145 SE +/- 0.014, N = 3 SE +/- 0.093, N = 8 SE +/- 0.009, N = 3 SE +/- 0.046, N = 3 5.467 5.605 5.613 5.475 MIN: 5.2 / MAX: 15.12 MIN: 5.18 / MAX: 15.5 MIN: 5.27 / MAX: 15.21 MIN: 5.22 / MAX: 14.58 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: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: resnet18 1 2 3 4 4 8 12 16 20 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.30, N = 3 SE +/- 0.17, N = 4 15.52 15.13 15.44 15.31 MIN: 14.6 / MAX: 25.5 MIN: 14.5 / MAX: 16.23 MIN: 14.48 / MAX: 25.18 MIN: 14.42 / MAX: 23.74 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 1 2 3 4 0.8188 1.6376 2.4564 3.2752 4.094 SE +/- 0.056, N = 3 SE +/- 0.036, N = 8 SE +/- 0.041, N = 3 SE +/- 0.021, N = 3 3.639 3.613 3.548 3.579 MIN: 3.45 / MAX: 13.35 MIN: 3.31 / MAX: 12.85 MIN: 3.38 / MAX: 4.56 MIN: 3.41 / MAX: 13.05 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: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 1 2 3 4 0.4865 0.973 1.4595 1.946 2.4325 SE +/- 0.016, N = 3 SE +/- 0.018, N = 8 SE +/- 0.009, N = 3 SE +/- 0.021, N = 3 2.162 2.132 2.110 2.120 MIN: 2.08 / MAX: 12.03 MIN: 1.96 / MAX: 11.61 MIN: 2.04 / MAX: 2.79 MIN: 2.02 / MAX: 11.83 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
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 1 2 3 4 12 24 36 48 60 SE +/- 0.29, N = 3 SE +/- 0.15, N = 3 SE +/- 0.62, N = 3 SE +/- 0.02, N = 3 51.18 51.65 50.55 51.71 MIN: 50.67 / MAX: 52.1 MIN: 51.22 / MAX: 52.21 MIN: 49.21 / MAX: 51.4 MIN: 51.45 / MAX: 51.95 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 1 2 3 4 7 14 21 28 35 SE +/- 0.57, N = 3 SE +/- 0.21, N = 8 SE +/- 0.17, N = 3 SE +/- 0.21, N = 3 27.74 28.04 27.94 27.49 MIN: 25.63 / MAX: 38.02 MIN: 26.28 / MAX: 38.11 MIN: 26.8 / MAX: 37.92 MIN: 26.2 / MAX: 114.44 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: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: efficientnet-b0 1 2 3 4 1.224 2.448 3.672 4.896 6.12 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 4 5.44 5.34 5.36 5.39 MIN: 5.13 / MAX: 13.04 MIN: 5.11 / MAX: 6.02 MIN: 5.13 / MAX: 6.14 MIN: 5.11 / MAX: 6.21 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 2 3 4 6 12 18 24 30 SE +/- 0.44, N = 3 SE +/- 0.64, N = 3 SE +/- 0.06, N = 3 SE +/- 0.38, N = 4 25.85 25.59 25.38 25.38 MIN: 24.4 / MAX: 35.2 MIN: 24.1 / MAX: 36 MIN: 24.45 / MAX: 34.42 MIN: 23.94 / MAX: 34.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: alexnet 1 2 3 4 3 6 9 12 15 SE +/- 0.27, N = 3 SE +/- 0.29, N = 3 SE +/- 0.25, N = 3 SE +/- 0.17, N = 4 12.13 11.91 12.05 12.07 MIN: 11.21 / MAX: 13.9 MIN: 11.22 / MAX: 20.72 MIN: 11.15 / MAX: 13.2 MIN: 11.19 / MAX: 21.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 3840 x 2160 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 3840 x 2160 - Renderer: OpenGL 1 2 3 4 14 28 42 56 70 SE +/- 0.22, N = 3 SE +/- 0.24, N = 3 SE +/- 0.26, N = 3 SE +/- 0.15, N = 3 60.3 60.9 60.6 59.9
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 1 2 3 4 50 100 150 200 250 SE +/- 0.68, N = 3 SE +/- 0.49, N = 3 SE +/- 0.15, N = 3 SE +/- 0.35, N = 3 211.66 212.99 210.13 213.41 MIN: 210.66 / MAX: 213.22 MIN: 212.06 / MAX: 214.18 MIN: 209.71 / MAX: 210.55 MIN: 212.77 / MAX: 214.35 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: mnasnet 1 2 3 4 0.8955 1.791 2.6865 3.582 4.4775 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 4 3.92 3.93 3.96 3.98 MIN: 3.82 / MAX: 4.57 MIN: 3.81 / MAX: 4.46 MIN: 3.8 / MAX: 10.68 MIN: 3.81 / MAX: 12.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 1920 x 1080 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1080 - Renderer: OpenGL 1 2 3 4 20 40 60 80 100 SE +/- 0.52, N = 3 SE +/- 0.60, N = 3 SE +/- 0.83, N = 3 SE +/- 0.23, N = 3 93.7 93.8 94.3 94.8
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: blazeface 1 2 3 4 0.4073 0.8146 1.2219 1.6292 2.0365 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 4 1.81 1.79 1.81 1.81 MIN: 1.76 / MAX: 2.24 MIN: 1.74 / MAX: 2.35 MIN: 1.73 / MAX: 2.34 MIN: 1.74 / MAX: 2.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 1920 x 1200 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1200 - Renderer: OpenGL 1 2 3 4 20 40 60 80 100 SE +/- 0.64, N = 3 SE +/- 0.55, N = 3 SE +/- 0.64, N = 3 SE +/- 0.56, N = 3 93.2 93.5 92.7 93.7
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 4 0.9833 1.9666 2.9499 3.9332 4.9165 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 4.34 4.37 4.35 4.33 MIN: 4.13 / MAX: 5.23 MIN: 4.14 / MAX: 12.66 MIN: 4.13 / MAX: 5.11 MIN: 4.12 / MAX: 5.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: regnety_400m 1 2 3 4 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 4 9.96 9.94 10.03 10.00 MIN: 9.61 / MAX: 10.66 MIN: 9.61 / MAX: 18.41 MIN: 9.71 / MAX: 10.66 MIN: 9.64 / MAX: 18.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 2560 x 1440 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 2560 x 1440 - Renderer: OpenGL 1 2 3 4 20 40 60 80 100 SE +/- 0.50, N = 3 SE +/- 0.43, N = 3 SE +/- 0.86, N = 3 SE +/- 0.45, N = 3 81.4 81.6 81.6 82.1
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 1 2 3 4 50 100 150 200 250 SE +/- 0.17, N = 3 SE +/- 0.83, N = 3 SE +/- 2.10, N = 3 SE +/- 0.52, N = 3 225.07 223.86 223.16 223.91 MIN: 221.35 / MAX: 236.01 MIN: 221.25 / MAX: 235.85 MIN: 215.11 / MAX: 245.22 MIN: 222.1 / MAX: 228.25 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: shufflenet-v2 1 2 3 4 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.01, N = 3 SE +/- 0.00, N = 2 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 4.15 4.16 4.15 4.18 MIN: 4.04 / MAX: 4.79 MIN: 4.05 / MAX: 4.74 MIN: 4.02 / MAX: 4.84 MIN: 4.04 / MAX: 4.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 2560 x 1440 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 2560 x 1440 - Renderer: Vulkan 1 2 3 4 20 40 60 80 100 SE +/- 0.30, N = 3 SE +/- 0.31, N = 3 SE +/- 0.58, N = 3 SE +/- 0.21, N = 3 83.9 83.7 83.9 83.3
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 4 0.9338 1.8676 2.8014 3.7352 4.669 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 4 4.15 4.13 4.15 4.15 MIN: 4 / MAX: 4.93 MIN: 3.99 / MAX: 4.74 MIN: 4 / MAX: 4.97 MIN: 3.98 / MAX: 4.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
GravityMark Resolution: 1920 x 1080 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1080 - Renderer: Vulkan 1 2 3 4 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 SE +/- 0.29, N = 3 SE +/- 0.38, N = 3 93.6 93.8 93.9 94.0
GravityMark Resolution: 1920 x 1200 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 1920 x 1200 - Renderer: Vulkan 1 2 3 4 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 SE +/- 0.27, N = 3 SE +/- 0.38, N = 3 94.4 94.0 94.1 94.1
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: vgg16 1 2 3 4 14 28 42 56 70 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.12, N = 4 60.21 60.40 60.20 60.24 MIN: 59.16 / MAX: 68.71 MIN: 59.24 / MAX: 67.73 MIN: 58.58 / MAX: 68.87 MIN: 58.54 / MAX: 69.6 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 1 2 3 4 500 1000 1500 2000 2500 SE +/- 3.21, N = 3 SE +/- 2.66, N = 3 SE +/- 4.60, N = 3 SE +/- 3.84, N = 3 2400.99 2402.10 2396.49 2402.68 MIN: 2340.25 / MAX: 2486.65 MIN: 2335.18 / MAX: 2487.17 MIN: 2350.03 / MAX: 2475.58 MIN: 2336.02 / MAX: 2481.49 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
GravityMark Resolution: 3840 x 2160 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.1b Resolution: 3840 x 2160 - Renderer: Vulkan 1 2 3 4 14 28 42 56 70 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 63.6 63.5 63.6 63.6
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210525 Target: CPU - Model: googlenet 1 2 3 4 4 8 12 16 20 SE +/- 0.50, N = 3 SE +/- 0.18, N = 3 SE +/- 0.52, N = 3 SE +/- 0.33, N = 4 14.22 13.68 14.04 13.78 MIN: 12.76 / MAX: 16.22 MIN: 12.81 / MAX: 14.91 MIN: 12.63 / MAX: 22.69 MIN: 12.5 / MAX: 22.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Phoronix Test Suite v10.8.4