NVIDIA GeForce GTX 1080 CUDA Linux Compute GPGPU Testing

NVIDIA GeForce GTX 1080 CUDA benchmarking including deep learning on Pascal. Benchmarks by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1606116-HA-CUDATESTI01
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
NVIDIA GPU Compute 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
GeForce GTX 960
June 11 2016
 
GeForce GTX 970
June 11 2016
 
GeForce GTX 980
June 11 2016
 
GeForce GTX 980 Ti
June 11 2016
 
GeForce GTX TITAN X
June 11 2016
 
GeForce GTX 1080
June 11 2016
 
Invert Hiding All Results Option
 

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


NVIDIA GeForce GTX 1080 CUDA Linux Compute GPGPU TestingOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon E3-1280 v5 @ 4.00GHz (8 Cores)MSI C236A WORKSTATION (MS-7998) v1.0Intel Sky Lake16384MBSamsung SSD 950 PRO 256GBeVGA NVIDIA GeForce GTX 960 2043MB (1277/3505MHz)eVGA NVIDIA GeForce GTX 970 4091MB (1163/3505MHz)NVIDIA GeForce GTX 980 4091MB (1126/3505MHz)NVIDIA GeForce GTX 980 Ti 6139MB (999/3505MHz)NVIDIA GeForce GTX TITAN X 12283MB (1001/3505MHz)GeForce 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 8.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GeForce GTX 1080 CUDA Linux Compute GPGPU Testing BenchmarksSystem Logs- --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 - Scaling Governor: intel_pstate performance- GeForce GTX 960: GPU Compute Cores: 1024- GeForce GTX 970: GPU Compute Cores: 1664- GeForce GTX 980: GPU Compute Cores: 2048- GeForce GTX 980 Ti: GPU Compute Cores: 2816- GeForce GTX TITAN X: GPU Compute Cores: 3072- GeForce GTX 1080: GPU Compute Cores: 2560- GeForce GTX 960: GPU Compute Cores: 1024.- GeForce GTX 970: GPU Compute Cores: 1664.- GeForce GTX 980: GPU Compute Cores: 2048.- GeForce GTX 980 Ti: GPU Compute Cores: 2816.- GeForce GTX TITAN X: GPU Compute Cores: 3072.- GeForce GTX 1080: GPU Compute Cores: 2560.

GeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080Result OverviewPhoronix Test Suite100%155%210%264%319%SHOC Scalable HeterOgeneous ComputingCaffe AlexNetSHOC Scalable HeterOgeneous ComputingCUDA Mini-NbodyCUDA Mini-NbodyCUDA Mini-NbodyCUDA Mini-NbodyCUDA Mini-NbodySHOC Scalable HeterOgeneous ComputingSHOC Scalable HeterOgeneous ComputingCUDA - Max SP FlopsCUDACUDA - MD5 HashSOA Data LayoutF.D.T.ZOriginalCache BlockingLoop UnrollingCUDA - FFT SPCUDA - T.R.B

NVIDIA GeForce GTX 1080 CUDA Linux Compute GPGPU Testingcaffe: CUDAshoc: CUDA - FFT SPshoc: CUDA - MD5 Hashshoc: CUDA - Max SP Flopsshoc: CUDA - Texture Read Bandwidthcuda-mini-nbody: Originalcuda-mini-nbody: Cache Blockingcuda-mini-nbody: Loop Unrollingcuda-mini-nbody: SOA Data Layoutcuda-mini-nbody: Flush Denormals To ZeroGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108028134.07189.143.882944.94381.0582.2936.3035.7181.2781.1923567.70265.175.474316.43351.3252.0426.7526.3857.0957.2015504.53292.786.534999.85332.1646.5124.9124.6351.0250.4412011.27302.767.816144.29348.3635.3519.6919.6442.0442.1011397.13322.578.436886.69352.0533.0918.6718.7138.6938.528959.77461.2811.989397.41528.4130.5114.0214.5228.5828.58OpenBenchmarking.org

Caffe AlexNet

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CUDAGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10806K12K18K24K30KSE +/- 2.72, N = 3SE +/- 1758.76, N = 6SE +/- 17.87, N = 3SE +/- 7.42, N = 3SE +/- 26.29, N = 3SE +/- 3.43, N = 328134.0723567.7015504.5312011.2711397.138959.771. (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
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CUDAGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10805K10K15K20K25KMin: 28128.9 / Avg: 28134.07 / Max: 28138.1Min: 17616.4 / Avg: 23567.7 / Max: 31101.2Min: 15469.2 / Avg: 15504.53 / Max: 15526.8Min: 11999.7 / Avg: 12011.27 / Max: 12025.1Min: 11369.5 / Avg: 11397.13 / Max: 11449.7Min: 8953 / Avg: 8959.77 / Max: 8964.151. (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

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe AlexNet 2016-06-11Build: CPU OnlyXeon E3-1280 v5 - CPU Only400K800K1200K1600K2000KSE +/- 4001.26, N = 317872071. (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

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: FFT SPGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080100200300400500SE +/- 1.12, N = 3SE +/- 0.05, N = 3SE +/- 0.60, N = 3SE +/- 4.36, N = 5SE +/- 0.29, N = 3SE +/- 2.81, N = 3189.14265.17292.78302.76322.57461.281. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: FFT SPGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108080160240320400Min: 187.37 / Avg: 189.14 / Max: 191.2Min: 265.09 / Avg: 265.17 / Max: 265.24Min: 291.57 / Avg: 292.78 / Max: 293.43Min: 285.52 / Avg: 302.76 / Max: 308.6Min: 322.01 / Avg: 322.57 / Max: 322.96Min: 457.55 / Avg: 461.28 / Max: 466.781. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: MD5 HashGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10803691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.885.476.537.818.4311.981. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft
OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: MD5 HashGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10803691215Min: 3.88 / Avg: 3.88 / Max: 3.88Min: 5.47 / Avg: 5.47 / Max: 5.47Min: 6.52 / Avg: 6.53 / Max: 6.54Min: 7.81 / Avg: 7.81 / Max: 7.81Min: 8.43 / Avg: 8.43 / Max: 8.43Min: 11.97 / Avg: 11.98 / Max: 121. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Max SP FlopsGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10802K4K6K8K10KSE +/- 7.67, N = 3SE +/- 1.66, N = 3SE +/- 11.01, N = 3SE +/- 21.31, N = 3SE +/- 41.66, N = 3SE +/- 88.40, N = 32944.944316.434999.856144.296886.699397.411. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Max SP FlopsGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108016003200480064008000Min: 2936.86 / Avg: 2944.94 / Max: 2960.28Min: 4314.49 / Avg: 4316.43 / Max: 4319.73Min: 4986.99 / Avg: 4999.85 / Max: 5021.77Min: 6122.8 / Avg: 6144.29 / Max: 6186.9Min: 6844.47 / Avg: 6886.69 / Max: 6970Min: 9290.02 / Avg: 9397.41 / Max: 9572.741. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Texture Read BandwidthGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080110220330440550SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.47, N = 3SE +/- 0.24, N = 3SE +/- 1.11, N = 3SE +/- 1.22, N = 3381.05351.32332.16348.36352.05528.411. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: CUDA - Benchmark: Texture Read BandwidthGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108090180270360450Min: 380.86 / Avg: 381.05 / Max: 381.35Min: 351.26 / Avg: 351.32 / Max: 351.36Min: 331.29 / Avg: 332.16 / Max: 332.91Min: 347.88 / Avg: 348.36 / Max: 348.62Min: 350.69 / Avg: 352.05 / Max: 354.26Min: 525.98 / Avg: 528.41 / Max: 529.821. (CXX) g++ options: -O2 -lSHOCCommon -lcudadevrt -lcudart_static -lrt -lpthread -ldl -lcufft

CUDA Mini-Nbody

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108020406080100SE +/- 0.27, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 382.2952.0446.5135.3533.0930.51
OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10801632486480Min: 81.88 / Avg: 82.29 / Max: 82.81Min: 51.79 / Avg: 52.04 / Max: 52.22Min: 46.2 / Avg: 46.51 / Max: 46.69Min: 34.93 / Avg: 35.35 / Max: 35.59Min: 32.84 / Avg: 33.09 / Max: 33.44Min: 30.42 / Avg: 30.51 / Max: 30.68

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Cache BlockingGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080816243240SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.16, N = 3SE +/- 0.30, N = 3SE +/- 0.20, N = 3SE +/- 0.01, N = 336.3026.7524.9119.6918.6714.02
OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Cache BlockingGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080816243240Min: 36.27 / Avg: 36.3 / Max: 36.31Min: 26.75 / Avg: 26.75 / Max: 26.76Min: 24.59 / Avg: 24.91 / Max: 25.1Min: 19.37 / Avg: 19.69 / Max: 20.29Min: 18.43 / Avg: 18.67 / Max: 19.07Min: 14 / Avg: 14.02 / Max: 14.04

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Loop UnrollingGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080816243240SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 335.7126.3824.6319.6418.7114.52
OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Loop UnrollingGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 1080816243240Min: 35.66 / Avg: 35.71 / Max: 35.76Min: 26.35 / Avg: 26.38 / Max: 26.41Min: 24.23 / Avg: 24.63 / Max: 24.9Min: 19.4 / Avg: 19.64 / Max: 19.94Min: 18.46 / Avg: 18.71 / Max: 19.05Min: 14.5 / Avg: 14.52 / Max: 14.57

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: SOA Data LayoutGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108020406080100SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 381.2757.0951.0242.0438.6928.58
OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: SOA Data LayoutGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10801632486480Min: 81.09 / Avg: 81.27 / Max: 81.42Min: 57.07 / Avg: 57.09 / Max: 57.11Min: 50.84 / Avg: 51.02 / Max: 51.28Min: 41.81 / Avg: 42.04 / Max: 42.21Min: 38.57 / Avg: 38.69 / Max: 38.79Min: 28.51 / Avg: 28.58 / Max: 28.67

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Flush Denormals To ZeroGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 108020406080100SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.22, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 381.1957.2050.4442.1038.5228.58
OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: Flush Denormals To ZeroGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX TITAN XGeForce GTX 10801530456075Min: 81.12 / Avg: 81.19 / Max: 81.33Min: 57.11 / Avg: 57.2 / Max: 57.38Min: 50.08 / Avg: 50.44 / Max: 50.84Min: 42.01 / Avg: 42.1 / Max: 42.15Min: 38.35 / Avg: 38.52 / Max: 38.71Min: 28.46 / Avg: 28.58 / Max: 28.65