ncnn 10900k dec Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012191-HA-NCNN1090077&rdt .
ncnn 10900k dec 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 5 Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads) Gigabyte Z490 AORUS MASTER (F3 BIOS) Intel Comet Lake PCH 16GB Samsung SSD 970 EVO 250GB Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz) Realtek ALC1220 ASUS MG28U Intel + Intel Wi-Fi 6 AX201 Ubuntu 20.10 5.8.0-31-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.6 Mesa 20.2.1 (LLVM 11.0.0) 1.2.131 GCC 10.2.0 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 2.3 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
ncnn 10900k dec 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 1 2 3 4 5 16.21 4.93 3.87 4.41 3.81 5.89 1.60 18.76 61.98 13.74 12.06 24.38 24.05 17.89 13.24 16.68 4.94 3.83 4.35 3.80 5.91 1.58 12.88 62.03 13.41 12.01 24.20 24.09 17.86 12.98 16.19 4.94 3.88 4.37 3.79 5.90 1.59 12.89 62.09 13.43 12.00 24.08 23.67 17.74 13.19 16.12 4.96 3.88 4.40 3.93 6.00 1.61 12.86 61.66 13.46 12.00 24.30 23.81 17.85 13.15 16.42 4.98 3.91 4.48 3.92 5.92 1.60 12.84 62.18 13.43 11.99 24.34 23.74 17.88 13.16 16.20 4.97 3.88 4.36 3.79 5.87 1.57 12.85 62.50 13.46 12.00 24.36 23.96 17.82 13.02 16.13 4.98 3.87 4.41 3.82 5.83 1.59 13.02 62.39 13.45 12.02 24.09 23.82 17.83 13.15 16.15 4.96 3.91 4.43 3.83 5.86 1.59 12.99 62.51 13.48 12.04 24.09 23.79 17.83 13.23 16.17 4.99 3.92 4.43 3.83 5.86 1.59 12.88 62.23 13.44 12.02 24.08 23.75 17.88 12.98 16.16 4.87 3.88 4.38 3.87 5.90 1.59 12.96 62.28 13.55 11.97 24.03 23.76 17.76 13.11 OpenBenchmarking.org
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 1 2 3 4 5 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 16.21 16.19 16.42 16.13 16.17 MIN: 16.02 / MAX: 16.98 MIN: 16.12 / MAX: 16.95 MIN: 16.1 / MAX: 17.16 MIN: 15.83 / MAX: 17.26 MIN: 15.99 / MAX: 16.97 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 1 2 3 4 5 1.1228 2.2456 3.3684 4.4912 5.614 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.93 4.94 4.98 4.98 4.99 MIN: 4.69 / MAX: 5.98 MIN: 4.66 / MAX: 6.31 MIN: 4.83 / MAX: 6.23 MIN: 4.85 / MAX: 6.2 MIN: 4.86 / MAX: 6.41 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 1 2 3 4 5 0.882 1.764 2.646 3.528 4.41 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 3.87 3.88 3.91 3.87 3.92 MIN: 3.8 / MAX: 5.15 MIN: 3.81 / MAX: 5.37 MIN: 3.83 / MAX: 5.53 MIN: 3.68 / MAX: 5.34 MIN: 3.87 / MAX: 4.98 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 1 2 3 4 5 1.008 2.016 3.024 4.032 5.04 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 4.41 4.37 4.48 4.41 4.43 MIN: 4.29 / MAX: 5.6 MIN: 4.31 / MAX: 5.75 MIN: 4.33 / MAX: 5.58 MIN: 4.36 / MAX: 5.73 MIN: 4.35 / MAX: 5.39 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 1 2 3 4 5 0.882 1.764 2.646 3.528 4.41 SE +/- 0.00, N = 2 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.81 3.79 3.92 3.82 3.83 MIN: 3.77 / MAX: 4.58 MIN: 3.76 / MAX: 5.14 MIN: 3.77 / MAX: 5.14 MIN: 3.78 / MAX: 5.23 MIN: 3.79 / MAX: 4.87 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 1 2 3 4 5 1.332 2.664 3.996 5.328 6.66 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.89 5.90 5.92 5.83 5.86 MIN: 5.65 / MAX: 10.92 MIN: 5.67 / MAX: 7.36 MIN: 5.83 / MAX: 7.12 MIN: 5.63 / MAX: 7.06 MIN: 5.67 / MAX: 7.34 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 1 2 3 4 5 0.36 0.72 1.08 1.44 1.8 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.60 1.59 1.60 1.59 1.59 MIN: 1.57 / MAX: 1.81 MIN: 1.57 / MAX: 1.64 MIN: 1.57 / MAX: 2.96 MIN: 1.57 / MAX: 1.63 MIN: 1.57 / MAX: 1.63 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 1 2 3 4 5 5 10 15 20 25 SE +/- 5.74, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 18.76 12.89 12.84 13.02 12.88 MIN: 12.6 / MAX: 2024.54 MIN: 12.59 / MAX: 13.73 MIN: 12.5 / MAX: 20.39 MIN: 12.66 / MAX: 13.92 MIN: 12.59 / MAX: 13.85 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 1 2 3 4 5 14 28 42 56 70 SE +/- 0.30, N = 3 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.28, N = 3 SE +/- 0.11, N = 3 61.98 62.09 62.18 62.39 62.23 MIN: 61.46 / MAX: 75.82 MIN: 61.46 / MAX: 63.12 MIN: 61.69 / MAX: 67.41 MIN: 61.82 / MAX: 63.73 MIN: 61.76 / MAX: 74.65 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 1 2 3 4 5 4 8 12 16 20 SE +/- 0.25, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 13.74 13.43 13.43 13.45 13.44 MIN: 13.23 / MAX: 20.94 MIN: 13.25 / MAX: 14.26 MIN: 13.21 / MAX: 14.31 MIN: 13.23 / MAX: 14.24 MIN: 13.23 / MAX: 14.66 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 1 2 3 4 5 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 12.06 12.00 11.99 12.02 12.02 MIN: 11.91 / MAX: 20.31 MIN: 11.85 / MAX: 13.25 MIN: 11.85 / MAX: 19.49 MIN: 11.9 / MAX: 12.81 MIN: 11.91 / MAX: 13.1 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 1 2 3 4 5 6 12 18 24 30 SE +/- 0.30, N = 3 SE +/- 0.02, N = 3 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 24.38 24.08 24.34 24.09 24.08 MIN: 23.64 / MAX: 25.8 MIN: 23.56 / MAX: 25.79 MIN: 23.65 / MAX: 26.1 MIN: 23.89 / MAX: 24.87 MIN: 23.56 / MAX: 24.92 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 1 2 3 4 5 6 12 18 24 30 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 24.05 23.67 23.74 23.82 23.75 MIN: 23.51 / MAX: 25.63 MIN: 23.42 / MAX: 24.62 MIN: 23.49 / MAX: 31.58 MIN: 23.44 / MAX: 26.33 MIN: 23.35 / MAX: 24.75 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 1 2 3 4 5 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 17.89 17.74 17.88 17.83 17.88 MIN: 17.63 / MAX: 18.61 MIN: 17.62 / MAX: 18.48 MIN: 17.65 / MAX: 18.51 MIN: 17.45 / MAX: 18.66 MIN: 17.79 / MAX: 21.81 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 1 2 3 4 5 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 13.24 13.19 13.16 13.15 12.98 MIN: 12.86 / MAX: 21.35 MIN: 12.93 / MAX: 14.63 MIN: 12.96 / MAX: 14.78 MIN: 12.88 / MAX: 14.64 MIN: 12.85 / MAX: 14.39 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 2 3 4 5 4 8 12 16 20 SE +/- 0.26, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 16.68 16.12 16.20 16.15 16.16 MIN: 16.08 / MAX: 17.74 MIN: 16 / MAX: 23.01 MIN: 16 / MAX: 16.85 MIN: 16 / MAX: 16.99 MIN: 16 / MAX: 18.26 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 1 2 3 4 5 1.1183 2.2366 3.3549 4.4732 5.5915 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 4.94 4.96 4.97 4.96 4.87 MIN: 4.73 / MAX: 6.5 MIN: 4.67 / MAX: 6.31 MIN: 4.81 / MAX: 6.41 MIN: 4.68 / MAX: 6.28 MIN: 4.68 / MAX: 6.19 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 2 3 4 5 0.8798 1.7596 2.6394 3.5192 4.399 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 3.83 3.88 3.88 3.91 3.88 MIN: 3.7 / MAX: 4.86 MIN: 3.81 / MAX: 6.21 MIN: 3.83 / MAX: 5.24 MIN: 3.83 / MAX: 4.98 MIN: 3.79 / MAX: 4.93 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 1 2 3 4 5 0.9968 1.9936 2.9904 3.9872 4.984 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 4.35 4.40 4.36 4.43 4.38 MIN: 4.29 / MAX: 5.67 MIN: 4.29 / MAX: 5.8 MIN: 4.3 / MAX: 5.78 MIN: 4.35 / MAX: 5.33 MIN: 4.28 / MAX: 5.65 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 2 3 4 5 0.8843 1.7686 2.6529 3.5372 4.4215 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 3.80 3.93 3.79 3.83 3.87 MIN: 3.75 / MAX: 5.21 MIN: 3.76 / MAX: 5.53 MIN: 3.75 / MAX: 5.18 MIN: 3.79 / MAX: 4.87 MIN: 3.74 / MAX: 5.57 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 3 4 5 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.91 6.00 5.87 5.86 5.90 MIN: 5.69 / MAX: 7.29 MIN: 5.65 / MAX: 6.95 MIN: 5.64 / MAX: 7.33 MIN: 5.66 / MAX: 6.89 MIN: 5.66 / MAX: 9.61 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 3 4 5 0.3623 0.7246 1.0869 1.4492 1.8115 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.58 1.61 1.57 1.59 1.59 MIN: 1.55 / MAX: 2.05 MIN: 1.56 / MAX: 2.34 MIN: 1.51 / MAX: 2.35 MIN: 1.57 / MAX: 1.81 MIN: 1.56 / MAX: 2.04 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 3 4 5 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 12.88 12.86 12.85 12.99 12.96 MIN: 12.56 / MAX: 13.75 MIN: 12.56 / MAX: 13.19 MIN: 12.56 / MAX: 13.71 MIN: 12.59 / MAX: 14.33 MIN: 12.63 / MAX: 13.88 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 1 2 3 4 5 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.39, N = 3 SE +/- 0.24, N = 3 SE +/- 0.14, N = 3 62.03 61.66 62.50 62.51 62.28 MIN: 61.82 / MAX: 66.09 MIN: 61.46 / MAX: 68.61 MIN: 61.54 / MAX: 63.92 MIN: 61.75 / MAX: 69.6 MIN: 61.92 / MAX: 71.61 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 2 3 4 5 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 13.41 13.46 13.46 13.48 13.55 MIN: 13.23 / MAX: 14.19 MIN: 13.27 / MAX: 14.21 MIN: 13.24 / MAX: 14.24 MIN: 13.24 / MAX: 14.9 MIN: 13.21 / MAX: 14.28 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 1 2 3 4 5 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 12.01 12.00 12.00 12.04 11.97 MIN: 11.9 / MAX: 12.84 MIN: 11.9 / MAX: 12.85 MIN: 11.83 / MAX: 12.84 MIN: 11.91 / MAX: 12.83 MIN: 11.88 / MAX: 12.72 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 2 3 4 5 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.22, N = 3 SE +/- 0.26, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 24.20 24.30 24.36 24.09 24.03 MIN: 23.56 / MAX: 25.4 MIN: 23.53 / MAX: 25.57 MIN: 23.6 / MAX: 25.7 MIN: 23.62 / MAX: 26.99 MIN: 23.62 / MAX: 24.8 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 2 3 4 5 6 12 18 24 30 SE +/- 0.35, N = 3 SE +/- 0.11, N = 3 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 24.09 23.81 23.96 23.79 23.76 MIN: 23.45 / MAX: 115.98 MIN: 23.41 / MAX: 24.81 MIN: 23.48 / MAX: 24.81 MIN: 23.46 / MAX: 24.73 MIN: 23.46 / MAX: 30.92 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 1 2 3 4 5 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 17.86 17.85 17.82 17.83 17.76 MIN: 17.35 / MAX: 21.4 MIN: 17.41 / MAX: 18.98 MIN: 17.6 / MAX: 25.31 MIN: 17.42 / MAX: 18.65 MIN: 17.51 / MAX: 18.65 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 1 2 3 4 5 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.30, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 12.98 13.15 13.02 13.23 13.11 MIN: 12.8 / MAX: 20.28 MIN: 12.7 / MAX: 20.78 MIN: 12.83 / MAX: 14.53 MIN: 12.95 / MAX: 14.31 MIN: 12.94 / MAX: 14.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4