ncnn mnn 3950x AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS) and Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2208150-NE-NCNNMNN3937 .
ncnn mnn 3950x Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VII HERO (WI-FI) (3103 BIOS) AMD Starship/Matisse 16GB Samsung SSD 970 EVO 250GB + 32GB Flash Drive Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1260/1750MHz) AMD Ellesmere HDMI Audio DELL S2409W Intel I211 + Realtek RTL8822BE 802.11a/b/g/n/ac Ubuntu 20.04 5.11.0-43-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.13 4.6 Mesa 20.0.8 (LLVM 10.0.0) 1.2.128 GCC 9.3.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-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-HskZEa/gcc-9-9.3.0/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 Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ncnn mnn 3950x 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: CPU - vision_transformer ncnn: CPU - FastestDet 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 ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet a b c 2.848 4.937 32.467 7.812 5.317 4.056 35.526 15.46 5.44 4.76 5.52 4.90 7.30 2.4 17.42 53.10 14.41 11.14 23.74 27.62 23.06 16.78 146.15 6.46 9.38 4.43 5.62 3.61 5.04 18.49 1.94 11.41 18.00 5.95 7.70 13.04 11.68 8.41 9.14 377.05 3.22 2.841 4.937 33.150 7.775 5.407 3.752 35.518 15.44 5.45 4.75 5.54 4.87 7.32 2.40 17.46 53.03 14.50 11.18 23.65 27.46 23.13 16.83 145.70 6.68 9.34 4.43 5.65 3.71 5.03 18.44 1.95 11.60 18.15 5.94 7.71 12.98 11.66 8.44 9.10 378.95 3.17 2.821 4.677 32.725 7.652 5.438 3.745 36.020 15.50 5.45 4.75 5.51 4.93 7.38 2.40 17.35 53.12 14.52 11.18 23.69 27.36 23.01 16.78 146.34 6.43 9.29 4.45 5.62 3.57 5.08 18.58 1.96 11.59 18.22 5.90 7.72 13.00 11.68 8.43 9.12 377.51 3.21 OpenBenchmarking.org
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: mobilenetV3 a b c 0.6408 1.2816 1.9224 2.5632 3.204 SE +/- 0.038, N = 3 SE +/- 0.014, N = 3 SE +/- 0.018, N = 3 2.848 2.841 2.821 MIN: 2.73 / MAX: 4.37 MIN: 2.75 / MAX: 3.06 MIN: 2.73 / MAX: 5.05 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: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.0 Model: squeezenetv1.1 a b c 1.1108 2.2216 3.3324 4.4432 5.554 SE +/- 0.036, N = 3 SE +/- 0.033, N = 3 SE +/- 0.166, N = 3 4.937 4.937 4.677 MIN: 4.71 / MAX: 21.4 MIN: 4.72 / MAX: 5.92 MIN: 4.39 / MAX: 6.82 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 2.0 Model: resnet-v2-50 a b c 8 16 24 32 40 SE +/- 0.45, N = 3 SE +/- 0.13, N = 3 SE +/- 0.35, N = 3 32.47 33.15 32.73 MIN: 29.56 / MAX: 45.88 MIN: 30.5 / MAX: 49.94 MIN: 30.01 / MAX: 48.89 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 2.0 Model: SqueezeNetV1.0 a b c 2 4 6 8 10 SE +/- 0.105, N = 3 SE +/- 0.073, N = 3 SE +/- 0.084, N = 3 7.812 7.775 7.652 MIN: 7.46 / MAX: 20.39 MIN: 7.45 / MAX: 9.84 MIN: 7.35 / MAX: 23.64 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 2.0 Model: MobileNetV2_224 a b c 1.2236 2.4472 3.6708 4.8944 6.118 SE +/- 0.085, N = 3 SE +/- 0.037, N = 3 SE +/- 0.035, N = 3 5.317 5.407 5.438 MIN: 5.04 / MAX: 7.26 MIN: 5.21 / MAX: 10.71 MIN: 5.21 / MAX: 17.23 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 2.0 Model: mobilenet-v1-1.0 a b c 0.9126 1.8252 2.7378 3.6504 4.563 SE +/- 0.299, N = 3 SE +/- 0.043, N = 3 SE +/- 0.028, N = 3 4.056 3.752 3.745 MIN: 3.59 / MAX: 50.47 MIN: 3.64 / MAX: 20.1 MIN: 3.64 / MAX: 6.12 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 2.0 Model: inception-v3 a b c 8 16 24 32 40 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 SE +/- 0.10, N = 3 35.53 35.52 36.02 MIN: 34.03 / MAX: 103.82 MIN: 33.72 / MAX: 51.6 MIN: 34.52 / MAX: 51.71 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 20220729 Target: CPU - Model: mobilenet a b c 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 15.46 15.44 15.50 MIN: 15.17 / MAX: 17.01 MIN: 15.12 / MAX: 27.48 MIN: 15.14 / MAX: 67.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 a b c 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 5.44 5.45 5.45 MIN: 5.31 / MAX: 6.31 MIN: 5.32 / MAX: 6.78 MIN: 5.31 / MAX: 15.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 a b c 1.071 2.142 3.213 4.284 5.355 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 4.76 4.75 4.75 MIN: 4.67 / MAX: 8.48 MIN: 4.66 / MAX: 6.12 MIN: 4.63 / MAX: 20.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 a b c 1.2465 2.493 3.7395 4.986 6.2325 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.52 5.54 5.51 MIN: 5.4 / MAX: 6.11 MIN: 5.45 / MAX: 7.44 MIN: 5.4 / MAX: 6.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet a b c 1.1093 2.2186 3.3279 4.4372 5.5465 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 4.90 4.87 4.93 MIN: 4.81 / MAX: 5.04 MIN: 4.79 / MAX: 5.69 MIN: 4.79 / MAX: 12.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 a b c 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 7.30 7.32 7.38 MIN: 7.2 / MAX: 7.93 MIN: 7.22 / MAX: 7.98 MIN: 7.18 / MAX: 63.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface a b c 0.54 1.08 1.62 2.16 2.7 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 2.40 2.40 2.40 MIN: 2.36 / MAX: 2.58 MIN: 2.36 / MAX: 2.54 MIN: 2.36 / MAX: 2.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet a b c 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 17.42 17.46 17.35 MIN: 16.22 / MAX: 26.9 MIN: 16.21 / MAX: 68.84 MIN: 16.08 / MAX: 19.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 a b c 12 24 36 48 60 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 53.10 53.03 53.12 MIN: 51 / MAX: 67 MIN: 50.97 / MAX: 63.9 MIN: 50.96 / MAX: 60.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 a b c 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 14.41 14.50 14.52 MIN: 13.93 / MAX: 15.9 MIN: 13.99 / MAX: 30.06 MIN: 13.88 / MAX: 17.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet a b c 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 11.14 11.18 11.18 MIN: 10.69 / MAX: 12.61 MIN: 10.65 / MAX: 27.17 MIN: 10.59 / MAX: 12.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 a b c 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 23.74 23.65 23.69 MIN: 23.07 / MAX: 40.31 MIN: 23.15 / MAX: 25.5 MIN: 23.12 / MAX: 32.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny a b c 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.19, N = 3 SE +/- 0.20, N = 3 27.62 27.46 27.36 MIN: 26.17 / MAX: 36.37 MIN: 26.01 / MAX: 39.75 MIN: 25.81 / MAX: 67.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd a b c 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 23.06 23.13 23.01 MIN: 20.83 / MAX: 30.07 MIN: 20.81 / MAX: 32.42 MIN: 20.71 / MAX: 31.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m a b c 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 16.78 16.83 16.78 MIN: 16.64 / MAX: 18.85 MIN: 16.66 / MAX: 18.76 MIN: 16.54 / MAX: 33.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer a b c 30 60 90 120 150 SE +/- 0.83, N = 3 SE +/- 0.60, N = 3 SE +/- 0.24, N = 3 146.15 145.70 146.34 MIN: 143.57 / MAX: 164.8 MIN: 143.74 / MAX: 164.73 MIN: 143.99 / MAX: 161.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet a b c 2 4 6 8 10 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 6.46 6.68 6.43 MIN: 6.27 / MAX: 6.87 MIN: 6.61 / MAX: 7.28 MIN: 6.25 / MAX: 7.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet a b c 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 9.38 9.34 9.29 MIN: 8.83 / MAX: 36.65 MIN: 8.91 / MAX: 18.4 MIN: 8.86 / MAX: 28.72 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 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 a b c 1.0013 2.0026 3.0039 4.0052 5.0065 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 4.43 4.43 4.45 MIN: 4.09 / MAX: 9.07 MIN: 4.09 / MAX: 10.66 MIN: 4.08 / MAX: 12.74 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 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 a b c 1.2713 2.5426 3.8139 5.0852 6.3565 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 5.62 5.65 5.62 MIN: 5.09 / MAX: 7.52 MIN: 5.07 / MAX: 14.38 MIN: 5.08 / MAX: 8.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 a b c 0.8348 1.6696 2.5044 3.3392 4.174 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 3.61 3.71 3.57 MIN: 3.13 / MAX: 4.29 MIN: 3.12 / MAX: 18.24 MIN: 3.13 / MAX: 4.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet a b c 1.143 2.286 3.429 4.572 5.715 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.04 5.03 5.08 MIN: 4.47 / MAX: 9.88 MIN: 4.46 / MAX: 10.1 MIN: 4.47 / MAX: 10.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 a b c 5 10 15 20 25 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 18.49 18.44 18.58 MIN: 17.53 / MAX: 31.63 MIN: 17.56 / MAX: 30.09 MIN: 17.54 / MAX: 31.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface a b c 0.441 0.882 1.323 1.764 2.205 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.94 1.95 1.96 MIN: 1.9 / MAX: 5.27 MIN: 1.91 / MAX: 5.7 MIN: 1.92 / MAX: 5.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet a b c 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 11.41 11.60 11.59 MIN: 9.64 / MAX: 19.49 MIN: 9.66 / MAX: 18.46 MIN: 9.65 / MAX: 18.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 a b c 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 18.00 18.15 18.22 MIN: 17.4 / MAX: 27.33 MIN: 17.42 / MAX: 31.97 MIN: 17.39 / MAX: 30.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 a b c 1.3388 2.6776 4.0164 5.3552 6.694 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 5.95 5.94 5.90 MIN: 5.23 / MAX: 19.39 MIN: 5.23 / MAX: 13.79 MIN: 5.24 / MAX: 12.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet a b c 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.70 7.71 7.72 MIN: 7.25 / MAX: 12.12 MIN: 7.25 / MAX: 13.21 MIN: 7.26 / MAX: 12.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 a b c 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 13.04 12.98 13.00 MIN: 11.44 / MAX: 23.92 MIN: 11.42 / MAX: 21.3 MIN: 11.45 / MAX: 25.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny a b c 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 11.68 11.66 11.68 MIN: 10.78 / MAX: 24.97 MIN: 10.86 / MAX: 23.92 MIN: 10.81 / MAX: 27.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd a b c 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 8.41 8.44 8.43 MIN: 7.7 / MAX: 16.57 MIN: 7.68 / MAX: 16.47 MIN: 7.69 / MAX: 15.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m a b c 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 9.14 9.10 9.12 MIN: 9 / MAX: 13.8 MIN: 8.99 / MAX: 13.11 MIN: 8.99 / MAX: 13.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer a b c 80 160 240 320 400 SE +/- 0.16, N = 3 SE +/- 1.25, N = 3 SE +/- 0.36, N = 3 377.05 378.95 377.51 MIN: 364.74 / MAX: 405.75 MIN: 365.44 / MAX: 413.13 MIN: 364 / MAX: 405.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet a b c 0.7245 1.449 2.1735 2.898 3.6225 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 3.22 3.17 3.21 MIN: 3.01 / MAX: 12.12 MIN: 2.96 / MAX: 5.36 MIN: 3.01 / MAX: 10.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Phoronix Test Suite v10.8.5