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.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2102268-HA-0226NCNN255 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson Processor: ARMv8 Cortex-A57 @ 1.48GHz (4 Cores), Motherboard: NVIDIA Jetson Nano 2GB Developer Kit, Memory: 2048MB, Disk: 62GB SA64G, Graphics: NVIDIA Tegra X1, Monitor: PL2493H, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 18.04, Kernel: 4.9.201-tegra (aarch64), Desktop: LXDE 0.9.3, Display Server: X Server 1.19.6, Display Driver: NVIDIA 32.5.1, OpenGL: 4.6.0, Vulkan: 1.2.131, Compiler: GCC 7.5.0 + CUDA 10.2, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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 -vProcessor Notes: Scaling Governor: tegra-cpufreq schedutil
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 30 60 90 120 150 SE +/- 8.81, N = 9 128.69 MIN: 110.63 / MAX: 563.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 9 18 27 36 45 SE +/- 3.32, N = 9 39.34 MIN: 31.73 / MAX: 161.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 8 16 24 32 40 SE +/- 3.40, N = 9 35.60 MIN: 28.96 / MAX: 475.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 6 12 18 24 30 SE +/- 1.31, N = 9 25.28 MIN: 21.19 / MAX: 89.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 8 16 24 32 40 SE +/- 1.83, N = 9 36.43 MIN: 30.35 / MAX: 169.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 16 32 48 64 80 SE +/- 2.88, N = 9 72.10 MIN: 65.88 / MAX: 161.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 3 6 9 12 15 SE +/- 0.49, N = 9 9.15 MIN: 7.63 / MAX: 94.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 20 40 60 80 100 SE +/- 4.15, N = 9 109.96 MIN: 96.92 / MAX: 288.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 110 220 330 440 550 SE +/- 9.92, N = 9 502.31 MIN: 456.26 / MAX: 1065.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 30 60 90 120 150 SE +/- 3.17, N = 9 113.47 MIN: 103.28 / MAX: 349.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 30 60 90 120 150 SE +/- 4.18, N = 9 122.03 MIN: 105.68 / MAX: 550.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 50 100 150 200 250 SE +/- 4.75, N = 9 247.29 MIN: 225.68 / MAX: 620.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 40 80 120 160 200 SE +/- 7.26, N = 9 180.49 MIN: 160.68 / MAX: 437.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 20 40 60 80 100 SE +/- 2.57, N = 9 93.60 MIN: 85.3 / MAX: 298.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson 15 30 45 60 75 SE +/- 5.57, N = 9 69.44 MIN: 54.15 / MAX: 431.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ARMv8 Cortex-A57 - NVIDIA Tegra X1 - NVIDIA Jetson Processor: ARMv8 Cortex-A57 @ 1.48GHz (4 Cores), Motherboard: NVIDIA Jetson Nano 2GB Developer Kit, Memory: 2048MB, Disk: 62GB SA64G, Graphics: NVIDIA Tegra X1, Monitor: PL2493H, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 18.04, Kernel: 4.9.201-tegra (aarch64), Desktop: LXDE 0.9.3, Display Server: X Server 1.19.6, Display Driver: NVIDIA 32.5.1, OpenGL: 4.6.0, Vulkan: 1.2.131, Compiler: GCC 7.5.0 + CUDA 10.2, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --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 -vProcessor Notes: Scaling Governor: tegra-cpufreq schedutil
Testing initiated at 26 February 2021 15:53 by user jetson.