0226ncnn

ARMv8 Cortex-A57 testing with a NVIDIA Jetson Nano 2GB Developer Kit and NVIDIA Tegra X1 on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2102268-HA-0226NCNN255.

0226ncnnProcessorMotherboardMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA JetsonARMv8 Cortex-A57 @ 1.48GHz (4 Cores)NVIDIA Jetson Nano 2GB Developer Kit2048MB62GB SA64GNVIDIA Tegra X1PL2493HRealtek RTL8111/8168/8411Ubuntu 18.044.9.201-tegra (aarch64)LXDE 0.9.3X Server 1.19.6NVIDIA 32.5.14.6.01.2.131GCC 7.5.0 + CUDA 10.2ext41920x1080OpenBenchmarking.org- Transparent Huge Pages: always- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only -v - Scaling Governor: tegra-cpufreq schedutil

0226ncnnncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson128.6939.3435.6025.2836.4372.109.15109.96502.31113.47122.03247.29180.4993.6069.44OpenBenchmarking.org

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson306090120150SE +/- 8.81, N = 9128.69MIN: 110.63 / MAX: 563.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson918273645SE +/- 3.32, N = 939.34MIN: 31.73 / MAX: 161.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson816243240SE +/- 3.40, N = 935.60MIN: 28.96 / MAX: 475.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson612182430SE +/- 1.31, N = 925.28MIN: 21.19 / MAX: 89.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson816243240SE +/- 1.83, N = 936.43MIN: 30.35 / MAX: 169.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson1632486480SE +/- 2.88, N = 972.10MIN: 65.88 / MAX: 161.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson3691215SE +/- 0.49, N = 99.15MIN: 7.63 / MAX: 94.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson20406080100SE +/- 4.15, N = 9109.96MIN: 96.92 / MAX: 288.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson110220330440550SE +/- 9.92, N = 9502.31MIN: 456.26 / MAX: 1065.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson306090120150SE +/- 3.17, N = 9113.47MIN: 103.28 / MAX: 349.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson306090120150SE +/- 4.18, N = 9122.03MIN: 105.68 / MAX: 550.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson50100150200250SE +/- 4.75, N = 9247.29MIN: 225.68 / MAX: 620.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson4080120160200SE +/- 7.26, N = 9180.49MIN: 160.68 / MAX: 437.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson20406080100SE +/- 2.57, N = 993.60MIN: 85.3 / MAX: 298.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson1530456075SE +/- 5.57, N = 969.44MIN: 54.15 / MAX: 431.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread


Phoronix Test Suite v10.8.4