cuda-testing

Intel Xeon E3-1280 v5 testing with a MSI C236A WORKSTATION (MS-7998) v1.0 and eVGA NVIDIA GeForce GTX 960 2043MB on Ubuntu 16.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1606119-PTS-CUDATEST14&grr&sro.

cuda-testingProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionGeForce GTX 1080GeForce GTX 980GeForce GTX 960Intel Xeon E3-1280 v5 @ 4.00GHz (8 Cores)MSI C236A WORKSTATION (MS-7998) v1.0Intel Sky Lake16384MBSamsung SSD 950 PRO 256GBGeForce GTX 1080 8187MB (909/5005MHz)Realtek ALC1150Intel ConnectionUbuntu 16.044.4.0-22-generic (x86_64)Unity 7.4.0NVIDIA 367.184.5.01.0.8GCC 5.3.1 20160413 + CUDA 8.0ext43840x2160NVIDIA GeForce GTX 980 4091MB (1126/3505MHz)eVGA NVIDIA GeForce GTX 960 2043MB (1277/3505MHz)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- GeForce GTX 1080: Scaling Governor: intel_pstate powersave- GeForce GTX 980: Scaling Governor: intel_pstate performance- GeForce GTX 960: Scaling Governor: intel_pstate powersaveOpenCL Details- GeForce GTX 1080: GPU Compute Cores: 2560- GeForce GTX 980: GPU Compute Cores: 2048- GeForce GTX 960: GPU Compute Cores: 1024System Details- GeForce GTX 1080: GPU Compute Cores: 2560.- GeForce GTX 980: GPU Compute Cores: 2048.- GeForce GTX 960: GPU Compute Cores: 1024.

cuda-testingcuda-mini-nbody: Flush Denormals To Zerocuda-mini-nbody: SOA Data Layoutcuda-mini-nbody: Loop Unrollingcuda-mini-nbody: Cache Blockingcuda-mini-nbody: Originalcaffe: CUDAshoc: CUDA - Texture Read Bandwidthshoc: CUDA - Bus Speed Readbackshoc: CUDA - Bus Speed Downloadshoc: CUDA - Max SP Flopsshoc: CUDA - MD5 Hashshoc: CUDA - FFT SPshoc: CUDA - TriadGeForce GTX 1080GeForce GTX 980GeForce GTX 960Xeon E3-1280 v5 - CPU Only28.5828.5814.5214.0230.518959.77528.4113.2212.539397.4111.98461.2814.8650.4451.0224.6324.9146.5115504.53332.1613.2212.534999.856.53292.7814.7481.1981.2735.7136.3082.2928134.07381.0513.2112.532944.943.88189.1414.361787207OpenBenchmarking.org

CUDA Mini-Nbody

Test: Flush Denormals To Zero

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Flush Denormals To ZeroGeForce GTX 1080GeForce GTX 960GeForce GTX 98020406080100SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 328.5881.1950.44

CUDA Mini-Nbody

Test: SOA Data Layout

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: SOA Data LayoutGeForce GTX 1080GeForce GTX 960GeForce GTX 98020406080100SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 328.5881.2751.02

CUDA Mini-Nbody

Test: Loop Unrolling

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Loop UnrollingGeForce GTX 1080GeForce GTX 960GeForce GTX 980816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 314.5235.7124.63

CUDA Mini-Nbody

Test: Cache Blocking

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Cache BlockingGeForce GTX 1080GeForce GTX 960GeForce GTX 980816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 314.0236.3024.91

CUDA Mini-Nbody

Test: Original

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalGeForce GTX 1080GeForce GTX 960GeForce GTX 98020406080100SE +/- 0.08, N = 3SE +/- 0.27, N = 3SE +/- 0.15, N = 330.5182.2946.51

Caffe AlexNet

Build: CUDA

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CUDAGeForce GTX 1080GeForce GTX 960GeForce GTX 980Xeon E3-1280 v5 - CPU Only400K800K1200K1600K2000KSE +/- 3.43, N = 3SE +/- 2.72, N = 3SE +/- 17.87, N = 3SE +/- 4001.26, N = 38959.7728134.0715504.531787207.001. (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

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Texture Read BandwidthGeForce GTX 1080GeForce GTX 960GeForce GTX 980110220330440550SE +/- 1.22, N = 3SE +/- 0.15, N = 3SE +/- 0.47, N = 3528.41381.05332.161. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Bus Speed ReadbackGeForce GTX 1080GeForce GTX 960GeForce GTX 9803691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 313.2213.2113.221. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Bus Speed DownloadGeForce GTX 1080GeForce GTX 960GeForce GTX 9803691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 312.5312.5312.531. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Max SP FlopsGeForce GTX 1080GeForce GTX 960GeForce GTX 9802K4K6K8K10KSE +/- 88.40, N = 3SE +/- 7.67, N = 3SE +/- 11.01, N = 39397.412944.944999.851. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: MD5 HashGeForce GTX 1080GeForce GTX 960GeForce GTX 9803691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 311.983.886.531. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: FFT SPGeForce GTX 1080GeForce GTX 960GeForce GTX 980100200300400500SE +/- 2.81, N = 3SE +/- 1.12, N = 3SE +/- 0.60, N = 3461.28189.14292.781. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

SHOC Scalable HeterOgeneous Computing

Target: CUDA - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: TriadGeForce GTX 1080GeForce GTX 960GeForce GTX 98048121620SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 314.8614.3614.741. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

Phoronix Test Suite v10.8.4