Caffe vs. nvCaffe On Jetson TX2

ARMv8 rev 3 testing with a quill and GP10B (nvgpu)/ on Ubuntu 16.04 via the Phoronix Test Suite. nvCaffe modifications. Tests for a future article

HTML result view exported from: https://openbenchmarking.org/result/1704219-TR-CAFFECUDA04.

Caffe vs. nvCaffe On Jetson TX2ProcessorMotherboardMemoryDiskGraphicsOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionCaffeNVIDIA nvCaffeARMv8 rev 3 @ 2.00GHz (6 Cores)quill8192MB31GB 032G34GP10B (nvgpu)/Ubuntu 16.044.4.15-tegra (aarch64)Unity 7.4.0X Server 1.18.3NVIDIA 27.1.04.5.01.0.8GCC 5.4.0 20160609 + CUDA 8.0ext43840x2160OpenBenchmarking.orgCompiler Details- --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,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 --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v Processor Details- Scaling Governor: tegra_cpufreq schedutil

Caffe vs. nvCaffe On Jetson TX2caffe: CUDA AlexNetcaffe: CUDA GooglenetCaffeNVIDIA nvCaffe143994301424120787237643OpenBenchmarking.org

Caffe

Build: CUDA AlexNet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2016-12-29Build: CUDA AlexNetCaffeNVIDIA nvCaffe30K60K90K120K150KSE +/- 441.73, N = 3SE +/- 119.84, N = 31439941207871. (CXX) g++ options: -pthread -fPIC -O2 -lcaffe -lglog -lgflags -lprotobuf -lboost_system -lboost_filesystem -lm -lhdf5_hl -lhdf5 -lleveldb -lsnappy -llmdb -lopencv_core -lopencv_highgui -lopencv_imgproc -lboost_thread -lstdc++ -lcblas -latlas

Caffe

Build: CUDA Googlenet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2016-12-29Build: CUDA GooglenetCaffeNVIDIA nvCaffe60K120K180K240K300KSE +/- 91.38, N = 3SE +/- 82.12, N = 33014242376431. (CXX) g++ options: -pthread -fPIC -O2 -lcaffe -lglog -lgflags -lprotobuf -lboost_system -lboost_filesystem -lm -lhdf5_hl -lhdf5 -lleveldb -lsnappy -llmdb -lopencv_core -lopencv_highgui -lopencv_imgproc -lboost_thread -lstdc++ -lcblas -latlas

Phoronix Test Suite v10.8.4