NVIDIA CUDA cuDNN Caffe vs. Intel CPUs On Linux Run

NVIDIA CUDA Caffe build versus CPU-only Caffe build with both AlexNet and GoogleNet. Tests by Michael Larabel and all tests on same system sans switching out CPUs for other CPU-only runs.

HTML result view exported from: https://openbenchmarking.org/result/1608296-LO-CUDA200NV70.

NVIDIA CUDA cuDNN Caffe vs. Intel CPUs On Linux RunProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionGeForce GTX TITAN XGeForce GTX 1080GeForce GTX 950Intel Xeon E5-2609 v4 @ 1.70GHz (8 Cores)MSI X99A WORKSTATION (MS-7A54) v1.0Intel Xeon E7 v4/Xeon16384MB3 x 120GB TOSHIBA-TR150NVIDIA GeForce GTX TITAN X 12288MB (1001/3505MHz)Realtek ALC1150Intel ConnectionUbuntu 16.044.4.0-34-generic (x86_64)Unity 7.4.0X Server 1.18.3NVIDIA 367.354.5.01.0.8GCC 5.4.0 20160609 + CUDA 8.0ext42560x1440NVIDIA GeForce GTX 1080 8192MB (1604/5005MHz)eVGA NVIDIA GeForce GTX 950 2048MB (1202/3304MHz)OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --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-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v Processor Details- Scaling Governor: intel_pstate performance

NVIDIA CUDA cuDNN Caffe vs. Intel CPUs On Linux Runcaffe: 200 - AlexNetcaffe: CPU AlexNetcaffe: 200 - Googlenetcaffe: CPU GooglenetGeForce GTX TITAN XGeForce GTX 1080GeForce GTX 950Xeon E5-2687W v3Core i7-5960XXeon E5-2609 v42297.706410.671990.285391.086141.3414154.9742719842719882560682560642476442476481465381465383162983162916031031603103OpenBenchmarking.org

Caffe AlexNet

Iterations: 200 - Build: AlexNet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Iterations: 200 - Build: AlexNetXeon E5-2687W v3Core i7-5960XXeon E5-2609 v4GeForce GTX TITAN XGeForce GTX 1080GeForce GTX 950200K400K600K800K1000KSE +/- 561.17, N = 3SE +/- 627.11, N = 3SE +/- 4812.82, N = 3SE +/- 4.23, N = 3SE +/- 3.77, N = 3SE +/- 7.74, N = 3427198.00424764.00831629.002297.701990.286141.341. (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 AlexNet

Build: CPU AlexNet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CPU AlexNetXeon E5-2687W v3Core i7-5960XXeon E5-2609 v4200K400K600K800K1000KSE +/- 561.17, N = 3SE +/- 627.11, N = 3SE +/- 4812.82, N = 34271984247648316291. (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 AlexNet

Iterations: 200 - Build: Googlenet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Iterations: 200 - Build: GooglenetXeon E5-2687W v3Core i7-5960XXeon E5-2609 v4GeForce GTX TITAN XGeForce GTX 1080GeForce GTX 950300K600K900K1200K1500KSE +/- 1923.36, N = 3SE +/- 737.95, N = 3SE +/- 2962.73, N = 3SE +/- 17.08, N = 3SE +/- 3.61, N = 3SE +/- 6.83, N = 3825606.00814653.001603103.006410.675391.0814154.971. (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 AlexNet

Build: CPU Googlenet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CPU GooglenetXeon E5-2687W v3Core i7-5960XXeon E5-2609 v4300K600K900K1200K1500KSE +/- 1923.36, N = 3SE +/- 737.95, N = 3SE +/- 2962.73, N = 382560681465316031031. (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