ncnn updated 5950x + rx 6800 xt AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS) and AMD SIENNA_CICHLID 16GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012187-PTS-NCNNUPDA37&gru&sor .
ncnn updated 5950x + rx 6800 xt Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver 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) (3003 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 + 2000GB AMD SIENNA_CICHLID 16GB (2575/1000MHz) AMD Device ab28 ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.10.0-051000rc6daily20201205-generic (x86_64) 20201204 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0) 1.2.145 GCC 9.3.0 ext4 3840x2160 OpenBenchmarking.org 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: 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
ncnn updated 5950x + rx 6800 xt ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 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 - shufflenet-v2 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 1 2 3 4 12.55 4.46 4.15 4.01 5.40 1.84 12.99 57.93 14.56 11.30 25.47 21.73 14.67 17.95 4.46 12.20 4.46 4.13 4.48 3.99 5.38 1.84 13.03 57.61 14.53 11.40 24.83 20.87 14.33 18.24 12.39 4.40 4.10 3.92 5.30 1.82 12.69 57.96 14.39 11.02 25.21 21.34 14.56 17.89 4.43 12.56 4.49 4.22 4.45 4.05 5.39 1.84 13.14 57.68 14.79 11.48 26.07 21.92 14.52 17.93 12.25 4.49 4.17 4.05 5.45 1.93 13.29 57.72 14.64 11.25 25.11 21.50 14.45 18.25 4.44 12.39 4.42 4.17 4.46 4.08 5.52 1.85 13.51 57.46 14.71 11.54 25.47 21.45 14.31 18.41 12.63 4.46 4.19 4.02 5.38 1.84 13.26 57.86 14.61 11.22 25.93 22.04 14.63 17.97 4.45 12.51 4.52 4.18 4.44 4.04 5.44 1.84 13.31 57.68 14.58 11.23 25.49 21.69 14.41 18.13 OpenBenchmarking.org
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 3 2 1 4 3 6 9 12 15 SE +/- 0.20, N = 3 SE +/- 0.17, N = 4 SE +/- 0.14, N = 15 SE +/- 0.11, N = 15 12.25 12.39 12.55 12.63 MIN: 11.91 / MAX: 13.08 MIN: 11.78 / MAX: 13.07 MIN: 11.79 / MAX: 49.77 MIN: 11.82 / MAX: 22.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 2 1 4 3 1.0103 2.0206 3.0309 4.0412 5.0515 SE +/- 0.02, N = 4 SE +/- 0.03, N = 15 SE +/- 0.03, N = 15 SE +/- 0.08, N = 3 4.40 4.46 4.46 4.49 MIN: 4.18 / MAX: 5.95 MIN: 4.22 / MAX: 15.2 MIN: 4.22 / MAX: 8.58 MIN: 4.24 / MAX: 6.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 2 1 3 4 0.9428 1.8856 2.8284 3.7712 4.714 SE +/- 0.03, N = 4 SE +/- 0.03, N = 15 SE +/- 0.07, N = 3 SE +/- 0.03, N = 15 4.10 4.15 4.17 4.19 MIN: 3.99 / MAX: 5.46 MIN: 4.02 / MAX: 6.24 MIN: 4.03 / MAX: 5.48 MIN: 4.06 / MAX: 27.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 2 1 4 3 0.9113 1.8226 2.7339 3.6452 4.5565 SE +/- 0.02, N = 4 SE +/- 0.04, N = 15 SE +/- 0.04, N = 15 SE +/- 0.11, N = 3 3.92 4.01 4.02 4.05 MIN: 3.77 / MAX: 4.94 MIN: 3.81 / MAX: 6.1 MIN: 3.8 / MAX: 5.62 MIN: 3.79 / MAX: 4.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 2 4 1 3 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.02, N = 4 SE +/- 0.03, N = 15 SE +/- 0.04, N = 15 SE +/- 0.11, N = 3 5.30 5.38 5.40 5.45 MIN: 5.2 / MAX: 6.55 MIN: 5.21 / MAX: 8.08 MIN: 5.21 / MAX: 11.8 MIN: 5.22 / MAX: 15.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 2 1 4 3 0.4343 0.8686 1.3029 1.7372 2.1715 SE +/- 0.03, N = 4 SE +/- 0.02, N = 15 SE +/- 0.01, N = 15 SE +/- 0.13, N = 3 1.82 1.84 1.84 1.93 MIN: 1.76 / MAX: 2.22 MIN: 1.77 / MAX: 3.69 MIN: 1.77 / MAX: 2.2 MIN: 1.78 / MAX: 54.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 2 1 4 3 3 6 9 12 15 SE +/- 0.04, N = 4 SE +/- 0.15, N = 15 SE +/- 0.22, N = 15 SE +/- 0.59, N = 3 12.69 12.99 13.26 13.29 MIN: 12.3 / MAX: 13.33 MIN: 12.32 / MAX: 24.45 MIN: 12.33 / MAX: 24.32 MIN: 12.37 / MAX: 45.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 3 4 1 2 13 26 39 52 65 SE +/- 0.35, N = 3 SE +/- 0.06, N = 15 SE +/- 0.07, N = 15 SE +/- 0.10, N = 4 57.72 57.86 57.93 57.96 MIN: 56.04 / MAX: 62.77 MIN: 56.32 / MAX: 97.91 MIN: 56.29 / MAX: 191.26 MIN: 56.88 / MAX: 68.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 2 1 4 3 4 8 12 16 20 SE +/- 0.09, N = 4 SE +/- 0.07, N = 15 SE +/- 0.08, N = 15 SE +/- 0.33, N = 3 14.39 14.56 14.61 14.64 MIN: 14.18 / MAX: 18.31 MIN: 14.13 / MAX: 27.65 MIN: 14.2 / MAX: 46.42 MIN: 14.21 / MAX: 16.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 2 4 3 1 3 6 9 12 15 SE +/- 0.14, N = 4 SE +/- 0.08, N = 15 SE +/- 0.35, N = 3 SE +/- 0.08, N = 15 11.02 11.22 11.25 11.30 MIN: 10.77 / MAX: 11.72 MIN: 10.81 / MAX: 32.79 MIN: 10.82 / MAX: 12.32 MIN: 10.78 / MAX: 33.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 3 2 1 4 6 12 18 24 30 SE +/- 0.48, N = 3 SE +/- 0.34, N = 4 SE +/- 0.18, N = 15 SE +/- 0.21, N = 15 25.11 25.21 25.47 25.93 MIN: 24.35 / MAX: 26.82 MIN: 24.42 / MAX: 36.51 MIN: 24.19 / MAX: 49.11 MIN: 24.27 / MAX: 38.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 2 3 1 4 5 10 15 20 25 SE +/- 0.42, N = 4 SE +/- 0.65, N = 3 SE +/- 0.24, N = 15 SE +/- 0.24, N = 15 21.34 21.50 21.73 22.04 MIN: 20.53 / MAX: 27.41 MIN: 20.57 / MAX: 31 MIN: 20.42 / MAX: 55.87 MIN: 20.45 / MAX: 31.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 3 2 4 1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.05, N = 4 SE +/- 0.07, N = 14 SE +/- 0.06, N = 13 14.45 14.56 14.63 14.67 MIN: 14.1 / MAX: 18.73 MIN: 14.05 / MAX: 30.66 MIN: 13.7 / MAX: 25.32 MIN: 14.05 / MAX: 17.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 2 1 4 3 4 8 12 16 20 SE +/- 0.10, N = 4 SE +/- 0.04, N = 15 SE +/- 0.05, N = 15 SE +/- 0.38, N = 3 17.89 17.95 17.97 18.25 MIN: 17.51 / MAX: 19.12 MIN: 17.59 / MAX: 28.89 MIN: 17.57 / MAX: 24.73 MIN: 17.57 / MAX: 28.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 2 3 4 1 1.0035 2.007 3.0105 4.014 5.0175 SE +/- 0.02, N = 4 SE +/- 0.01, N = 3 SE +/- 0.01, N = 14 SE +/- 0.01, N = 13 4.43 4.44 4.45 4.46 MIN: 4.34 / MAX: 5.3 MIN: 4.39 / MAX: 5.93 MIN: 4.38 / MAX: 9.11 MIN: 4.38 / MAX: 15.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet 1 3 4 2 3 6 9 12 15 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 15 SE +/- 0.17, N = 4 12.20 12.39 12.51 12.56 MIN: 11.86 / MAX: 12.96 MIN: 11.87 / MAX: 40.91 MIN: 11.8 / MAX: 30.08 MIN: 11.93 / MAX: 13.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 3 1 2 4 1.017 2.034 3.051 4.068 5.085 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 4 SE +/- 0.06, N = 15 4.42 4.46 4.49 4.52 MIN: 4.23 / MAX: 5.89 MIN: 4.2 / MAX: 5.95 MIN: 4.24 / MAX: 6.12 MIN: 4.19 / MAX: 45.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 1 3 4 2 0.9495 1.899 2.8485 3.798 4.7475 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 15 SE +/- 0.04, N = 4 4.13 4.17 4.18 4.22 MIN: 4.05 / MAX: 5.58 MIN: 4.02 / MAX: 35.81 MIN: 4 / MAX: 5.78 MIN: 4.12 / MAX: 5.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 4 2 3 1 1.008 2.016 3.024 4.032 5.04 SE +/- 0.01, N = 15 SE +/- 0.01, N = 4 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 4.44 4.45 4.46 4.48 MIN: 4.33 / MAX: 9.44 MIN: 4.37 / MAX: 7.43 MIN: 4.4 / MAX: 6.53 MIN: 4.41 / MAX: 5.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet 1 4 2 3 0.918 1.836 2.754 3.672 4.59 SE +/- 0.04, N = 3 SE +/- 0.05, N = 15 SE +/- 0.09, N = 4 SE +/- 0.08, N = 3 3.99 4.04 4.05 4.08 MIN: 3.83 / MAX: 5.27 MIN: 3.79 / MAX: 16.94 MIN: 3.83 / MAX: 5.37 MIN: 3.84 / MAX: 9.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 1 2 4 3 1.242 2.484 3.726 4.968 6.21 SE +/- 0.02, N = 3 SE +/- 0.07, N = 4 SE +/- 0.05, N = 15 SE +/- 0.10, N = 3 5.38 5.39 5.44 5.52 MIN: 5.28 / MAX: 6.9 MIN: 5.21 / MAX: 7.2 MIN: 5.23 / MAX: 9.54 MIN: 5.31 / MAX: 7.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface 1 2 4 3 0.4163 0.8326 1.2489 1.6652 2.0815 SE +/- 0.03, N = 3 SE +/- 0.04, N = 4 SE +/- 0.01, N = 15 SE +/- 0.03, N = 3 1.84 1.84 1.84 1.85 MIN: 1.79 / MAX: 2 MIN: 1.77 / MAX: 3.2 MIN: 1.77 / MAX: 4.09 MIN: 1.78 / MAX: 2.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet 1 2 4 3 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.48, N = 4 SE +/- 0.21, N = 15 SE +/- 0.57, N = 3 13.03 13.14 13.31 13.51 MIN: 12.5 / MAX: 15.43 MIN: 12.31 / MAX: 23.44 MIN: 12.22 / MAX: 21.56 MIN: 12.55 / MAX: 15.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 3 1 2 4 13 26 39 52 65 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 SE +/- 0.10, N = 4 SE +/- 0.08, N = 15 57.46 57.61 57.68 57.68 MIN: 56.2 / MAX: 65.71 MIN: 56.32 / MAX: 71.44 MIN: 56.61 / MAX: 63.83 MIN: 56.28 / MAX: 76.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 1 4 3 2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.11, N = 15 SE +/- 0.24, N = 3 SE +/- 0.27, N = 4 14.53 14.58 14.71 14.79 MIN: 14.36 / MAX: 16.66 MIN: 14 / MAX: 25.57 MIN: 14.34 / MAX: 15.61 MIN: 14.17 / MAX: 27.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet 4 1 2 3 3 6 9 12 15 SE +/- 0.08, N = 15 SE +/- 0.11, N = 3 SE +/- 0.21, N = 4 SE +/- 0.04, N = 3 11.23 11.40 11.48 11.54 MIN: 10.76 / MAX: 22.25 MIN: 11.13 / MAX: 23.55 MIN: 10.83 / MAX: 51.16 MIN: 11.24 / MAX: 11.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 1 3 4 2 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.65, N = 3 SE +/- 0.22, N = 15 SE +/- 0.30, N = 4 24.83 25.47 25.49 26.07 MIN: 24.5 / MAX: 25.66 MIN: 24.4 / MAX: 28.74 MIN: 24.17 / MAX: 47.83 MIN: 24.45 / MAX: 57.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny 1 3 4 2 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.61, N = 3 SE +/- 0.22, N = 15 SE +/- 0.56, N = 4 20.87 21.45 21.69 21.92 MIN: 20.56 / MAX: 23.42 MIN: 20.47 / MAX: 75.48 MIN: 20.33 / MAX: 31.85 MIN: 20.74 / MAX: 31.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd 3 1 4 2 4 8 12 16 20 SE +/- 0.26, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 15 SE +/- 0.06, N = 4 14.31 14.33 14.41 14.52 MIN: 13.61 / MAX: 22.82 MIN: 14.03 / MAX: 18.14 MIN: 13.63 / MAX: 25.57 MIN: 14.15 / MAX: 15.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m 2 4 1 3 5 10 15 20 25 SE +/- 0.07, N = 4 SE +/- 0.09, N = 15 SE +/- 0.37, N = 3 SE +/- 0.07, N = 3 17.93 18.13 18.24 18.41 MIN: 17.68 / MAX: 28.35 MIN: 17.55 / MAX: 31.68 MIN: 17.68 / MAX: 52.19 MIN: 18.12 / MAX: 20.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.5